{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## **Embracing Actionable Principles of AI Implementation: Pathways, Properties, and Human-Centric Approaches**","metadata":{}},{"cell_type":"markdown","source":"## **Introduction**\n\nArtificial Intelligence (AI) has developed at an estounding pace particularly during the past six months, unlocking potential for societal transformations in multiple industries. Whether you realize or not, algorithms are deciding who will get housing or financial opportunities, jobs, exam-taking eligibility, and use of medical care and treatment.\n\nCheck out the article below on how algorithms discriminate based on race so black patients had to be much sicker than white patients to be recommended for the same care.\n\n
\n\n \n \n \n AI Discrimination in Medical Care\n\n
\n\nBelow is another example where algorithms mischaracterized the medical needs of people with certain disabilities, which led to a miscalculation of the hours of aid to be received by residents in Arkansas, which led to extreme cuts to in-home care.\n\n
\n\nA study by Dr. Judy W. Gichoya, director of the Healthcare Innovations and Translational Informatics Lab at Emory University School of Medicine's Department of Radiology and Imaging Sciences, found that an AI tool trained on medical images learned patients' race, even when their doctors cannot. This opens up possiblities for future abuse and exploitation.\n\n
\n\nTo keep pace with this change, ethical considerations can no longer afford to be in the ideation stage, as we are at a point in time where ethical goals in AI implementation must translate into tangible actions with plans for implementation alongside the development of AI models themselves.\n\nAccording to Stanford's AI Index Report, the number of AI incidents and controversies has increased 26 times since 2012.\n\n
\n\nIn this essay, we will explore three papers published within the past two years:\n\n- Actionable Principles for Artificial Intelligence Policy: Three Pathways by Charlotte Stix from the Department of Industrial Engineering and Innovation Sciences, Eindhoven University of Technology, Eindhoven, The Netherlands, published on February 19, 2021 in Science and Engineering Ethics\n- Meaningful Human Control: Actionable Properties for AI System Development by Luciano Cavalcante Siebert, et. al from the Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, The Netherlands, published on May 18, 2022 in AI and Ethics\n- Human-Centered Artificial Intelligence in Education: Seeing the Invisible through the Visible by Stephen J.H. Yang, et. al from the Department of Computer Science and Informational Engineering, National Central University, Taiwan, published in 2021 in Computers and Education: Artificial Intelligence\n\nIn the paper, Actionable Principles for Artificial Intelligence Policy: Three Pathways, three approaches were suggested to create the \"actionable principles\":\n\n* Preliminary Landscape Assessment\n* Multi-Stakeholder Participation and Cross-Sectoral Feedback\n* Implementation and Operationalizability Support\n\nIn the paper, Meaningful Human Control: Actionable Properties for AI System Development, two necessary conditions for meaningful human control were brough up: tracking and tracing. The paper has also raised four properties of human-AI systems under meaningful human control:\n\n1. The human-AI system has an explicit moral operational design domain (moral ODD) and the AI agent adheres to the boundaries of this domain\n\n2. Human and AI agents have appropriate and mutually compatible representations of the human-AI system and its contaxt\n\n3. The relevant agents have ability and authority to control the system so that humans can act upon their responsibility\n\n4. Actions of the AI agents are explicitly linked to actions of humans who are aware of their moral responsibility\n\nOn the topic of human control, OpenAI has just published a blog on July 5, 2023, where they announced that a new team is bring together to control \"superintelligent\" AI.\n\n
\n\n\nAnd in the paper, Human-Centered Artificial Intelligence in Education: Seeing the Invisible through the Visible, the idea of making the \"invisible visible\" through AI is suggested to not only pertain to learning processes but also extend to track and improve ethical compliance in AI systems. AI ethics monitoring tools can help make the \"invisible\" aspects of ethical violations \"visible\", providing a pathway to mitigate the issues involved.\n\nThese three papers collectively underscore the need for a multi-dimensional, comprehensive, and forward-looking approach to AI policy-making and ethics. They highlight the challenges ahead and the relevant solutions to navigate the complex landscape of AI governance and ultimately fostering the development of AI systems that serve humanity's best interests.\n\n## **Three Pathways for Actionable Principles for AI Policy**\n\n**Preliminary Landscape Assessment**\n\nA landscape assessment could address practical hurdles of actionability that result out of a lack of access to sufficiently comprehensive and relevant information. It therefore constitutes the first pillar in formulating Actionable Principles for AI. During the last few years, more than a few cases illustrate how a lack of advanced landscape assessments can constrain the downtream impact of AI Ethics Principles. In 2017, New York City enacted bill \"Int. 1696\", establishing an Automated Decision Systems Task Force. The goal of this task force was to develop recommendations reviewing New York City's use of automated decision-making systems, including individual instances of \"harm\". However, the final report was subject to critique, which honed in on its weak recommendations that were partially related to the lack of resources the ADS has intially been allocated to conduct an appropriate landscape assessment.\n\n**Case Example - Biases in Loan Approval**\n\nLet's take the case of AI automated loan approval system. In order to ensure the fairness of the system, we will need the following information in our landscape assessment:\n\n**The Issue:**\n\nThe purpose of the system is to automate the loan approval process in a bank, which uses customer data such as credit score, income, and employment history to make approval decisions.\n\n**Identify Stakeholders**\n\nStakeholders can include:\n- Customers applying for loans\n- The Bank\n- Regulatory bodies for the banking industry\n- Society at large, as falsely approved loans can result in misuse of the loan proceeds for undesirable purposes\n\n**Potential Ethical Implications**\n\nFairness: The system must not discriminate against certain groups of customers over others\n\nTransparency: The decision-making process of the AI system should be explainable and understandable\n\nAccountability: There must be a mechanism to hold the system accountable for its decisions\n\nPrivacy: the system must respect the privacy of customer data\n\nWith respect to this ethical implications topic, [tvy13](https://www.kaggle.com/timvy13) has raised an [interesting question](https://www.kaggle.com/code/luckypen/actionable-ai-ethics/comments#2332335) with respect to **specific metrics** to measure the **ethical performance of AI systems**. Below is a brief on my response:\n\n**Explainability** is first to address, since we can't do anything without first understanding the system. For this purpose, there are the LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations) libraries we can use in Python.\n\nBelow is an article on the trending of Explainable AI:\n\n
\n\n**Auditability** is also important, which depends on the degree that all system actions are logged and available for review. A lot of software companies that offer machine learning services have audit trails to follow.\n\nThen, we can talk about the above four topics:\n\n**Fairness** can be measured through assessing equal representation of the different subgroups in a dataset. There are many ways to do this. One basic way is through the bar chart I have shown below.\n\n**Transparency** can be measured through availability, accessibility, and clarity of information provided about the AI system.\n\n**Accountability** could be measured by the AI system's compliance with relevant regulations, and the development team's willingness to take blames. This could be done through public enquiries for their view.\n\n**Privacy** can be measured by conducting privacy audits and making sure any data protection impact assessments are performed when necessary.\n\nOther areas of measuring an AI system's ethics performance can include reproducibility, robustness, and redress.\n\nI think **reproducibility** is as important as explainability, as some of the models yield different results each time you run them.\n\n**Robustness** could be done as a stress test on top of reproducibility, where we try to trick the system, and see if it will still produce the desirable results.\n\n**Redress** could be measured by observing if there are channels available for anyone seeking recourse in case they believe they have been treated unfairly.\n\n**Practical Case: Loan Approval System**\n\nBelow is an example case using the German Credit data to show fairness in the loan approval process. You can clearly see that single male individuals have more loans granted than any other personal trait categories. The full discussion on this topic is [here](https://open.substack.com/pub/luckypen/p/detecting-biases-in-loan-approvals?utm_campaign=post&utm_medium=web).","metadata":{}},{"cell_type":"markdown","source":"
\n\n \n \n \n Loan Approval Rate by Personal Trait\n\n
","metadata":{}},{"cell_type":"markdown","source":"**Practical Case: Predatory Loan Practices**\n\nOn the flip side of biased loan approval issues is the practice of predatory loan shops or loan sharks. They are specifically set up to target the most vulnerable populations of the country. Below is a visual of an exercise to use AI to monitor the borrowers' income and the interest rate they get on their loans, as well as an article that show the real problem of predatory loan practice in the country.\n\n
","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import accuracy_score, confusion_matrix\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import fetch_openml\n\n# Load the German Credit Data\ngerman_credit_data = fetch_openml(name='credit-g', version=1)\n\n# Convert data into dataframe and label encode categorical variables\ncredit_df = pd.DataFrame(data=np.c_[german_credit_data['data'], german_credit_data['target']],\n columns=german_credit_data['feature_names'] + ['target'])\n\nencoders = {} # A dictionary to hold LabelEncoder for each column\n\nfor col in credit_df.columns:\n if credit_df[col].dtype == 'object':\n encoders[col] = LabelEncoder() # Initialize a new encoder for this column\n credit_df[col] = encoders[col].fit_transform(credit_df[col].astype(str))\n\n# Split the data into training and testing sets\nX = credit_df.drop(['target'], axis=1)\ny = credit_df['target']\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n\n# Train a random forest classifier on the data\nrf = RandomForestClassifier(random_state=42)\nrf.fit(X_train, y_train)\n\n# Filter the test set to include only instances of personal_status\ngroup_feature = 'personal_status'\ngroup_values = credit_df['personal_status'].unique()\n\n# Initialize an empty list to store the count of predicted outputs equal to good for each group value\ngood_counts = []\n\n# Iterate through all the unique group values and get the count of predicted outputs equal to good for each group\nfor group_value in group_values:\n # Filter the test set to include only instances of the current group value\n group_filter = X_test[group_feature] == group_value\n X_test_group = X_test[group_filter]\n y_test_group = y_test[group_filter]\n \n # Use the model to predict the target variable for the filtered test set\n y_pred_group = rf.predict(X_test_group)\n \n # Get the count of predicted outputs equal to good for the current group\n good_count = np.sum(y_pred_group == 1)\n good_counts.append(good_count)\n\nstatus_counts = credit_df['personal_status'].value_counts()\n\n# Decode the personal status feature\nstatus_labels = encoders['personal_status'].inverse_transform([0, 1, 2, 3])\n\n# Define a dictionary mapping integer values to personal status labels\nstatus_dict = {0: 'male single',\n 1: 'female div/dep/mar',\n 2: 'male div/sep',\n 3: 'male mar/wid'}\n\n# Visualize the count of predicted outputs equal to good for each group using a bar chart\nplt.bar(range(len(status_counts)), good_counts)\nplt.xticks(ticks=[0, 1, 2, 3], labels=[status_dict[val] for val in range(len(status_dict))])\nplt.title('Count of Predicted Good Loans by Personal Status')\nplt.xlabel('Personal Status')\nplt.ylabel('Count')\nplt.show()","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2023-07-05T16:14:34.887964Z","iopub.execute_input":"2023-07-05T16:14:34.888406Z","iopub.status.idle":"2023-07-05T16:14:35.701727Z","shell.execute_reply.started":"2023-07-05T16:14:34.888375Z","shell.execute_reply":"2023-07-05T16:14:35.700597Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Reality Check**\n\nToday, [Benson Wamae](https://www.kaggle.com/bensonwamae) raised the below questions on bias in AI and the financial gap, as well as the education gap to understand AI in developing countries.\n\n[I am curious to know does the use of AI in the financial sector consider if biases are addressed so that the already wide financial gap does not continue to increase between the privileged and the underprivileged and how can the education gap to understanding AI be addressed in banks and in society as a whole especially in developing countries?](https://www.kaggle.com/code/luckypen/actionable-ai-ethics/comments#2334154)\n\nOn the issue of bias in AI and the financial gap, in addition to the potential lack of fairness in the loan scenario introduced above, AI could also be put to use in equalizing the pay gap. In 2015, Dr. Zara Nanu founded [Gapsquare](https://gapsquare.com/) aiming to use AI to track and analyze pay data by gender, ethnicity, disability, and other categories.\n\nOn the issue of AI education in developing countries, this [article](https://www.devex.com/news/how-artificial-intelligence-can-eventually-benefit-poorer-countries-104813) goes through several ways in which AI will eventually benefit developing countries, as well as current challenges, including:\n\n- Lack of data availability in developing countries\n- Incorporating responsible AI into ESG frameworks\n- Using AI to tackle cliamte issues in countries most in need\n- AI's own carbon footprint\n- Incorporating the voices of offline communities in training AI models such as ChatGPT\n\nThis will tie into the next section on multi-stakeholder participation and cross-sectoral feedback.","metadata":{}},{"cell_type":"markdown","source":"**Multi-Stakeholder Participation and Cross-Sectoral Feedback**\n\nThe predominant method of soliciting external expertise is to conduct a public consultation. Most commonly, consultations are conducted prior to the drafting stage. One issue with this kind of consultation is they shift the burden of knowing what could constitute \"useful\" information on the person or entity submitting information. They equally force the stakeholder group soliciting that information to already have a clear sense of the type of information they neeed, by virtue of asking the 'correct' questions or call for input. This can lead those submitting information to submit overly generic feedback, and the stakeholder group to ask overly broad questions. In the end, feedback received may be lacking information that is actually relevant.\n\nThe consultations prior to the drafting stage would also benefit from supplements from consultations during the drafting stage and after publication stage, which unfortunately are rarely made use of.\n\nConsultations during the drafting stage can serve to stress test an initial proposal and steer the work towards actionability, while consultations after publication can help in understanding reasons for a potential lack of implementation, or pinpoint omissions, outdated assumptions, or areas that require revision since the moment of publication.\n\nThrough the consultation process, the end goal is to achieve consensus on how AI should be implemented. However, it may be impossible to reach consensus despite broad stakeholder inclusion, as various groups depending on their background can end up using the same terminology, yet denoting different content spaces resulting in varying interpretations for their resolution. This creates the appearance of agreement at the drafting stage while causing difficulties at the implementation stage.\n\nAn example would be over 81% of AI Ethics Principle-type documents contained some recommendations in favour of 'safety' and 'security', in a study conducted by Fjeld et al. ([2020](https://doi.org/https://doi.org/10.2139/ssrn.3518482)). He argues that perceptions of what constitutes safety thresholds differ among people and societies. This would entail that AI would need to pass the median between all individual safety thresholds distributed across society, in order to be perceived as safe even if the concept is understood by all to denote the same thing.\n\nBelow is a sample survey in Python that would accomodate multi-stakeholder participation with multiple rounds of feedback entry. Please feel free to have a try at this interactive codebook by clicking on the image below. The hidden codes underneath is modified to remove the user input feature in order to run and save the codebook.","metadata":{}},{"cell_type":"markdown","source":" [](https://colab.research.google.com/drive/1Mq4o0l8ERgxfEg3et4JEquBMpnNtm2PL?usp=sharing)","metadata":{},"attachments":{"8f9779be-78a8-4cad-b78e-3f86f23f6107.png":{"image/png":"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"}}},{"cell_type":"code","source":"import pandas as pd\n\n# Define stakeholders\nstakeholders = ['Data Scientist', 'AI Ethicist', 'Safety Expert', 'End User', 'Regulator']\n\n# Define survey questions about safety\nquestions = {\n 'Pre-Drafting': {\n 'Q1': 'What are your main concerns about AI safety?',\n 'Q2': 'What measures do you think should be in place to ensure AI safety?'\n },\n 'During-Drafting': {\n 'Q3': 'Do you think the draft policy addresses your safety concerns?',\n 'Q4': 'What additions or changes would you suggest for the draft policy?'\n },\n 'Post-Publication': {\n 'Q5': 'Do you believe the final policy adequately addresses AI safety?',\n 'Q6': 'What further measures or improvements would you suggest?'\n }\n}\n\n# Specify the number of rounds for feedback collection\nnum_rounds = 2\n\n# Define a dictionary to store predefined responses\nresponses = {\n 'Data Scientist': 'Response from Data Scientist',\n 'AI Ethicist': 'Response from AI Ethicist',\n 'Safety Expert': 'Response from Safety Expert',\n 'End User': 'Response from End User',\n 'Regulator': 'Response from Regulator',\n}\n\n# Collect feedback\nfeedback = []\nfor round_num in range(num_rounds):\n for phase, phase_questions in questions.items():\n for question, description in phase_questions.items():\n for stakeholder in stakeholders:\n # Get stakeholder response from predefined responses\n response = responses[stakeholder]\n feedback.append([round_num + 1, phase, stakeholder, question, response])\n\n# Create a DataFrame from feedback\nfeedback_df = pd.DataFrame(feedback, columns=['Round', 'Phase', 'Stakeholder', 'Question', 'Response'])\nprint(feedback_df)","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2023-07-05T16:31:32.823129Z","iopub.execute_input":"2023-07-05T16:31:32.823615Z","iopub.status.idle":"2023-07-05T16:31:32.843839Z","shell.execute_reply.started":"2023-07-05T16:31:32.823580Z","shell.execute_reply":"2023-07-05T16:31:32.842295Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Implementation and Operationalizability Support**\n\nIn order to account for the broad impact of AI models, it is necessary to consider and provide both technical and non-technical tools and measures.\n\nTechnical measures can include explainable AI research, which can help to illuminate some of the underlying decision making processes within some AI systems, increasing an individual's ability to understand and challenge the AI's output.\n\nThey can include:\n\n- privacy-preserving measures, which serve to adequately protect and secure data used to develop and maintain a given AI system's functionality\n- requirements for sufficiently representative datasets (Flournoy et al. [2020](https://cset.georgetown.edu/wp-content/uploads/Building-Trust-Through-Testing.pdf)) to ensure both adequate functioning of an AI system in a real-world environment as well as to tackle bias introduced through inadequate datasets; or, describe testing and validation protocols and procedures that would support the fulfillment of the principles in question by a given AI system. Methods used to ensure privacy-preserving measures may cover:\n\n - adversarial testing by dedicated red teams (Brundage et al. [2020](http://arxiv.org/abs/2004.07213)),\n - evaluation of out of distribution robustness (Lohn [2020](http://arxiv.org/2009.00802)),\n - repeat testing within reasonable time spans once deployed, or\n - denoting adequate requirements for audit trails at all stages of the lifecycle of a given AI system (AI HLEG [2020](https://ec.europa.eu/digital-single-market/en/news/assessment-list-trustworthy-artificial-intelligence-altai-self-assessment))\n\nNon-technical measures can provide requirements and methods to increase society's participation in decision-making processes surrounding the development and deployment of AI systems, empowering them to flag and halt the development and application of AI systems with potential negative impacts. The dialogue with society could be carried out by developing and provisioning of relevant algorithm impact assessments. An example would be the [Canadian government's algorithmic impact assessment](https://open.canada.ca/aia-eia-js/?lang=en) or the [AI HLEG’s revised assessment list for trustworthy AI](https://digital-strategy.ec.europa.eu/en/library/assessment-list-trustworthy-artificial-intelligence-altai-self-assessment).\n\nThe provisioning of mechanisms for implementation can contribute to an actionability of underlying goals of an AI system documentation, thus it directly builds and expands on the earlier two elements: landscape assessment and multi-stakeholder engagement strategy. The three pathways together would form a prototype framework across the lifecycle of Actionable Principles - inception, development, post-publication.\n\nBelow is the Responsible AI Guidelines developed by the Defense Innovation Unit, an organization established to foster the incorporation of commercial technology in the US Department of Defense. The Responsible AI Guidelines are essentially a set of queries to be tackled during each phase of an AI project's lifecycle: planning, development, and deployment.\n\n
","metadata":{}},{"cell_type":"markdown","source":"## **Meaningful Human Control: Actionable Properties for AI System Development**\n\nThe third pathway above, implementation and operationalizability support for AI models, the paper Meaningful Human Control: Actionable Properties for AI System Development tackles the topic of AI implementation and operationalizability on an even more practical level. It identifies, through an interative process of abductive thinking, four actionable properties for AI-based systems under meaningful human control, using two application scenarios: automated vehicles and AI-based hiring:\n\n1. A system in which humans and AI algorithms interact should have an explicitly defined domain of morally loaded situations within which the system ought to operate.\n2. Humans and AI agents within the system should have appropriate and mutually compatible representations.\n3. Responsibility attributed to a human should be commensurate with that human's ability and authority to control the system.\n4. There should be explicit links between the actions of the AI agents and actions of humans who are aware of their moral responsibility.\n\nThe above when implemented appropriately should achieve the following two conditions for meaninful human control:\n\n1. Tracking: a human-AI system should be responsive to the human moral reasons relevant in the circumstances\n2. Tracing: a human-AI system's behavior, capabilities, and possible effects in the world should be traceable to a proper moral and technical understanding on the part of at least one relevant human agent who designs or interacts with the system.\n\nBelow is a visual representation of the above abductive thinking framework:\n\n
\n\n \n Framework of Abductive Thinking (Dorst, K.: The nature of design thinking. In: Design Thinking Research Symposium (2010). DAB Documents)\n\n
\n\nLet's dive into each of the four properties below:\n\n**Property #1: The human-AI system has an explicit moral operational design domain and the AI agent adheres to the boundaries of this domain**\n\nAs the human-AI system has to be \"responsive to relevant human moral reasons\", designers should consider a larger design space, one that captures the values and societal norms that must be considered and respected during both design and operation.\n\nThe concept of operational design domain is often used in the context of automated driving and refers to a set of contextual conditions under which a driving automation system is designed to function. Specific contextual properties of the automotive operational design domain include factors such as road structure, road users, road obstacles and environmental conditions, as well as human-vehicle interactions and expected vehicle interactions with pedestrians.\n\nAs simple as a hammer should be used to hammer nails and not to injure others, this moral concept may not be so clear cut when implemented in a complex human-AI system.\n\nIn the automated vehicle vase, the moral operational design domain should contain moral reasons representing safety (e.g. avoid road accidents), efficiency (e.g. reduce travel time), and personal freedom (e.g. enhance independence for seniors), among others. In the AI-based hiring context, moral reasons could include, from the employer's side, reducing discrimination or increasing the number of applicants in the recruitment process, while for the applicant's side, autonomy over self-representation could be considered very relevant.\n\nBelow are example codes for autonomous vehicle and AI-based Hiring. Please feel free to have a try at this interactive codebook by clicking on the image below. The hidden codes underneath is modified to remove the user input feature in order to run and save the codebook.\n\n [](https://colab.research.google.com/drive/1ZpzleiiY9_6mKSx2VTH_lnbDZA9U47TC?usp=sharing)","metadata":{},"attachments":{"cf04ded3-bda3-4dc9-b7b9-05e95e0b7711.png":{"image/png":"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"}}},{"cell_type":"code","source":"import random\n\nclass AutonomousVehicle:\n def __init__(self, safety_weight, efficiency_weight, personal_freedom_weight):\n # Initialize weights for each objective\n self.weights = {\n 'safety': safety_weight,\n 'efficiency': efficiency_weight,\n 'personal_freedom': personal_freedom_weight,\n }\n\n def score_action(self, action, environment):\n safety_score = self.evaluate_safety(action, environment)\n efficiency_score = self.evaluate_efficiency(action, environment)\n personal_freedom_score = self.evaluate_personal_freedom(action)\n\n total_score = (\n self.weights['safety'] * safety_score +\n self.weights['efficiency'] * efficiency_score +\n self.weights['personal_freedom'] * personal_freedom_score\n )\n\n return total_score\n\n def evaluate_safety(self, action, environment):\n # Dummy function: just returns a random value\n return random.random()\n\n def evaluate_efficiency(self, action, environment):\n # Dummy function: just returns a random value\n return random.random()\n\n def evaluate_personal_freedom(self, action):\n # Dummy function: just returns a random value\n return random.random()\n\n# Predefined weights\nsafety_weight = 0.7\nefficiency_weight = 0.2\npersonal_freedom_weight = 0.1\n\ncar = AutonomousVehicle(safety_weight, efficiency_weight, personal_freedom_weight)\n\n# Here we would normally collect real sensor data, but for this example let's use a dummy environment\nenvironment = {}\n\n# Again, in a real system we would have complex methods for determining possible actions.\n# For this example, let's just use a few dummy actions.\nactions = ['Increase speed', 'Decrease speed', 'Turn left', 'Turn right', 'Continue straight']\n\nprint(\"\\nScoring actions:\")\nfor action in actions:\n score = car.score_action(action, environment)\n print(f\"{action}: {score}\")","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2023-07-05T16:33:56.538446Z","iopub.execute_input":"2023-07-05T16:33:56.538879Z","iopub.status.idle":"2023-07-05T16:33:56.552584Z","shell.execute_reply.started":"2023-07-05T16:33:56.538849Z","shell.execute_reply":"2023-07-05T16:33:56.551107Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The assessment of whether and how an AI agent is confined to the moral operational design domain is not a binary check, but rather a contextualized and deliberate analysis of the interaction between the AI agent, human agents, and the social, physical, ethical and legal environment surrounding them. Humans therefore should have an understanding of such blurry boundaries of the moral operational design domain and their responsibility to meaningfully control the AI agent in this process, **which includes the possibility of deciding that the use of an AI agent is not acceptable in certain contexts.**\n\n**Property #2: Human and AI Agents have appropriate and mutually compatible representations of the human-AI system and its context**\n\nRepresentations that are mutually compatible between human and AI agents within the system allow the agents to have appropriate understanding of each other, the task, and the environment (Jonker, C.M., Van Riemsdijk, M.B., Vermeulen, B.: Shared Mental Models. In: De Vos, M., Fornara, N., Pitt, J.V., Vouros, G. (eds.) Coordination, Organizations, Institutions, and Norms in Agent Systems VI, pp. 132–151. Springer, Berlin (2011)), which facilitates agents to cooperate, adapt to changes, and respond to relevant human reasons.\n\nTo ensure safe operation of the system, agents should also have a shared representation of each other's abilities and limitations. Specifically, the AI agent should account for humans' inherent physical and cognitive limitations, while human agents should account for the AI agent's limitations to avoid issues such as overreliance (Lee, J.D., See, K.A.: Trust in Automation: Designing for Appropriate Reliance. Human Factors, 31 (2004). Crucial to achieve meaningful human control, these shared representations should include the human reasons identified in the moral operational design domain, which can change over time anc across contexts.\n\nIn order for the agents' shared representations to facilitate the system's tracking of relevant human reasons, the system designers first need to define which aspects of the system and its context each agent should have a representation of. A useful approach to determine the necessary representations and to translate the concept into practical design requirements is co-active design ([Johnson, M., Bradshaw, 2014](https://doi.org/10.5898/JHRI.3.1.Johnson)). Specific to building and maintaining shared representations, this approach provides guidelines on how to establish observability and predictability between the human and AI agents, including what needs to be communicated and when (Jonker, C.M., Van Riemsdijk, M.B., Vermeulen, B.: Shared Mental Models. In: De Vos, M., Fornara, N., Pitt, J.V., Vouros, G. (eds.) Coordination, Organizations, Institutions, and Norms in Agent Systems VI, pp. 132–151. Springer, Berlin (2011)).\n\nRepresentations can include practical matters such as task allocation, role distribution and system limits, but also understanding of how humans perceive the AI agents, human acceptance of and trust in the human-AI system, human values and social norms.\n\nThis should also include determining the appropriate level of representation. In the case of automated vehicles, in order for the vehicle to intereact with a pedestrian, the designers need to determine whether it suffices for the vehicle to have a representation of just the location of a pedestrian on the road and their movement trajectory, or also the height and age of that pedestrian, their goals and intentions.\n\nIn the case of AI-based hiring, a key aspect requiring shared representation is the meaning of competence. In particular, the meanings of soft skills, such as teamwork and creativity, are highly fluid, context-dependent, and contestable. Therefore, aligning the job-specific meaning of competence among job seekers, employers, and any AI agent involved in the hiring process is critical.\n\nOnce the representations required for each agent are defined, the design and engineering choices need to sufficiently take these into account. Ecological interface design can also leverage knowledge on human information processing to design human-AI interfaces that are optimally suited to convey complex data in a comprehensive manner ([Vicente, K.J., Rasmussen, 1992](https://doi.org/10.1109/21.156574)).\n\nFor the AI agents to have appropriate representations of human agents, the assumptions about human intentions and behavior adopted by AI agents, implicit or explicit, need to be validated. This can be aided by incorporating theoretically grounded and empirically validated models of humans in the interaction-planning algorithms of AI agents ([Schürmann, T., Beckerle, 2020](https://doi.org/10.3389/fpsyg.2020.561510), [Siebinga, O., Zgonnikov)](https://arxiv.org/abs/2109.13077), or by augmenting bottom-up, machine-learned representations with top-down symbolic representations ([Van Bekkum, M., de Boer, M., Van Harmelen, F., Meyer-Vitali, A., ten Teije, A.](https://arxiv.org/abs/2102.11965), [Marcus, G.](https://arxiv.org/abs/2002.06177)).\n\nAn alternative approach, value alignment (Gabriel, I.: Artificial intelligence, values, and alignment. Mind. Mach. 30(3), 411–437 (2020)), aims to mitigate the problems that arise when autonomous systems operate with inappropriate objectives. In particular, inverse reinforcement learning, which is often used in value alignment, aims to infer the \"reward function\" of an agent from observations of the agent's behavior, also in cooperative partial-information settings (Hadfield-Menell, D., Russell, S.J., Abbeel, P., Dragan, A.: Cooperative inverse reinforcement learning. Adv. Neural Inf. Process. Syst. 29 (2016)).\n\nBelow is an example code for inverse reinforcement learning. Please feel free to have a try at this interactive codebook by clicking on the image below. The hidden codes underneath is modified to remove the user input feature in order to run and save the codebook.\n\n [](https://colab.research.google.com/drive/1DuwMCaxDQsPp2VEucpGvWE4smAzLgfA0?usp=sharing)","metadata":{},"attachments":{"6de7b9a2-7eeb-4e04-8db3-517c8ff9c57e.png":{"image/png":"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"}}},{"cell_type":"code","source":"import numpy as np\nfrom scipy.optimize import minimize\n\ndef calculate_feature_expectations(traj_features, traj_probs):\n num_features = traj_features.shape[1]\n num_trajectories = traj_features.shape[0]\n\n feature_expectations = np.zeros(num_features)\n\n for i in range(num_trajectories):\n feature_expectations += traj_probs[i] * traj_features[i]\n\n return feature_expectations\n\ndef max_margin_planning(expert_features, expert_probs, agent_features):\n num_features = expert_features.shape[1]\n num_expert_trajectories = expert_features.shape[0]\n num_agent_trajectories = agent_features.shape[0]\n\n A = np.zeros((num_expert_trajectories + num_agent_trajectories, num_features))\n b = np.zeros(num_expert_trajectories + num_agent_trajectories)\n\n A[:num_expert_trajectories] = -expert_features\n b[:num_expert_trajectories] = -1.0\n\n A[num_expert_trajectories:] = agent_features\n b[num_expert_trajectories:] = 1.0\n\n c = np.zeros(num_features)\n\n result = minimize(lambda x: np.linalg.norm(x), c, constraints={'type': 'ineq', 'fun': lambda x: b - np.dot(A, x)})\n\n return result.x\n\n# Provide descriptions for trajectories and features\nprint(\"A trajectory represents the sequence of actions taken by an agent in a specific scenario.\")\nprint(\"A feature represents a characteristic or attribute used to describe a trajectory.\")\n\n# Example values for number of expert and agent trajectories\nnum_expert_trajectories = 3\nnum_agent_trajectories = 4\n\n# Initialize expert and agent trajectory arrays\nexpert_features = np.zeros((num_expert_trajectories, 2))\nexpert_probs = np.zeros(num_expert_trajectories)\nagent_features = np.zeros((num_agent_trajectories, 2))\n\n# Example expert trajectory information\nexpert_features = np.array([[0.6, 0.8], [0.7, 0.9], [0.8, 0.7]])\nexpert_probs = np.array([0.4, 0.3, 0.3])\n\n# Example agent trajectory information\nagent_features = np.array([[3.0, 5.0], [2.5, 6.0], [3.5, 4.5], [2.0, 5.5]])\n\n# Calculate expert feature expectations\nexpert_feature_expectations = calculate_feature_expectations(expert_features, expert_probs)\n\n# Apply MMP to get agent's reward function\nagent_reward_weights = max_margin_planning(expert_features, expert_probs, agent_features)\n\n# Evaluate agent's performance\nagent_feature_expectations = np.dot(agent_features, agent_reward_weights)\n\nprint(\"Expert Feature Expectations:\", expert_feature_expectations)\nprint(\"Agent Feature Expectations:\", agent_feature_expectations)","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2023-07-05T16:36:40.930058Z","iopub.execute_input":"2023-07-05T16:36:40.930556Z","iopub.status.idle":"2023-07-05T16:36:40.960779Z","shell.execute_reply.started":"2023-07-05T16:36:40.930505Z","shell.execute_reply":"2023-07-05T16:36:40.959584Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n**Property #3: The relevant humans and AI agents have ability and authority to control the system so that humans can act upon their responsibility**\n\n**Relevant humans should not be considered just mere subjects to be blamed in case something goes wrong**, but rather they should be in a position to act upon their moral responsibility by influencing the AI system through its operation and bring the system back to the moral operational design domain if needed.\n\nThis is only possible when the distribution of roles and control authority between humans and AI is consistent with their individual and combined abilities, including reasonable mechanism for overruling the AI agent through intervention and correcting behavior, setting new goals, or delegating sub-tasks.\n\n**In human-machine systems, the ability to control should not be smaller than control authority, and control authority should not be smaller than responsibility** (Flemisch, F., Heesen, M., Hesse, T., Kelsch, J., Schieben, A., Beller, J.: Towards a dynamic balance between humans and automation: authority, ability, responsibility and control in shared and cooperative control situations. Cognit. Technol. Work 14(1), 3–18 (2012)). The **ability of a human or AI agent** includes their skill and competence to perceive the state of a system and the environment. This also includes a way to acquire and analyze relevant information, to make a decision to act, and to perform that action appropriately. ([Parasuraman, R., et al., 2000](https://ieeexplore.ieee.org/document/844354)) Ability also includes the resources at their disposal, such as tools or time.\n\nThe understanding of an (AI or human) agent's ability is intrinsically related to the socio-technical context in which the system is embedded. Approaches such as the nature of activities (Santoni de Sio, F., et. al.: Who should enhance? Conceptual and normative dimensions of cognitive enhancement. HUMANA.MENTE J. Philos. Stud. 7(26), 179–197 (2014), [Santoni de Sio, F., 2016](https://doi.org/10.1007%2Fs11948-015-9715-4)), under the umbrella of Value Sensitive Design ([Friedman, B., Hendry, D.G., 2019](https://doi.org/10.7551%2Fmitpress%2F7585.001.0001)), can support the understanding of which set of tasks should be delegated or shared with AI agents, and which should be left exclusively to humans.\n\nThe second component mentioned above is **control authority**, which is the degree to which a human or AI agent is enabled to execute control. According to the above rule in ability to control not being smaller than control authority, which is not smaller than responsibility. An agent should be responsible only for tasks they have authority to perform, and they should have authority only over tasks they are able to perform. A key implication of this consistency is that control is exerted by the agent that has sufficient ability and authority, and more responsibility is carried by the agents that exert more control. While ability and authority are attributes that both human and AI agents possess, an important point to note is that **responsibility is a human-only quality**.\n\nConsider our autonomous vehicle case and AI-based hiring case in the context of authority to control, the driver may have final authority over a fully autonomous vehicle, but the driver's loss of situational awareness, or even skill degradation as a result of systematic lack of engagement in the driving task, will limit the driver's ability to exert control authority ([Heikoop, D.D., et. al., 2019](https://doi.org/10.1080/1463922X.2019.1574931), [Flemisch, F.et. al., 2012](https://doi.org/10.1007%2Fs10111-011-0191-6), [Kyriakidis, M., et. al., 2019](https://doi.org/10.1080/1463922X.2017.1293187)). The same may happen for a hiring manager with final authority over who to hire, if they merely sign off on the hiring recommendations of the AI agent, without substantively engaging in the assessment process themselves. **Humans must be empowered to act upon their moral responsibility.**\n\n**Property #4: Actions of the AI agents are explicitly linked to actions of humans who are aware of their moral responsibility**\n\nTo trace any consequence of the human-AI system’s operation to a proper moral understanding of relevant humans, there should be explicit, explainable and inspectable links between actions of the system and corresponding human morally loaded decisions and actions. As such, we argue that **moral understanding of the system’s effects should be demonstrated by, at least, those humans who make decisions with moral implications on the design, deployment, or use of the system, even if the actions that bring a human decision to life are executed by the AI agent**.\n\nThe links between actions of the AI system and the corresponding human morally loaded decisions and actions need to be explicitly identifiable in two ways:\n\n**Forward link**: Human should be aware of their moral responsibility associated with that decision\n\n**Backward Link**: For any consequence of the actions of the human-AI system, the human decisions and actions leading to that outcome should be readily identifiable.\n\nTo aid the link mapping process, values hierarchies ([Van de Poel, I, 2013](https://doi.org/10.1007/978-94-007-7762-0_20)) provide a structured and transparent approach to map relations between design choices and normative requirements. It visualizes the gradual specification of **broad moral notions**, such as moral responsibility, into **context-dependent properties or capabilities** the system should exhibit, and further into **concrete socio-technical design requirements**. Such a structured mapping can equip stakeholders with the means to deliberate design choices in a manner that explicitly links each choice to relevant aspects of moral responsibility.\n\nIn the autonomous vehicle case, consider an automated vehicle which slows down and pulls off the road after it recognizes a car accident ([Mecacci, G., 2020](https://doi.org/10.1007/s10676-019-09519-w)). The vehicle should immediately remind the driver of their duty to provide assistance to possible victims in the accident.\n\nIn the context of AI-based hiring, explanations of assessment scores in language that directly links observed job seeker performances to job-specific meanings of competence can help employers, job seekers, designers, and developers better outline the boundaries of moral operational design domain during design phase. This can help identify if there is misalignment between conceptions of competence among the human agents and the AI algorithm.\n\nIn complex socio-technical environments, the establishment of links between human moral awareness and actions of a human-AI system is complicated by the “problem of many hands”, which happens when more than one agent contributes to a decision. In case of unintended consequences of the AI agent’s actions, this complexity can hinder the backward link. This challenge calls for systemic, socio-technical design interventions that jointly consider social infrastructure, physical infrastructure, and the AI agents that are part of these infrastructures.\n\nMethods from social sciences, such as Actor-Network Theory (Latour, B., et al.: Reassembling the Social: An Introduction to Actor-Network-Theory. Oxford University Press, Oxford (2005)), can support the development of tracing networks of association amongst many actors, which can help understand how, for example, humans may offload value-laden behavior onto the technology around us. The paper “sociology of a door closer” (Johnson, J.: Mixing humans and nonhumans together: the sociology of a door-closer. Soc. Probl. 35(3), 298–310 (1988)), describes how we made door closers the element in the assembly that manifests politeness by ensuring the door closes softly and gradually, even as the human actors may barge through without any action to regulate the door.\n\nAlthough establishing explicit links between human decisions, human moral awareness, and actions of the AI agents is challenging, they allow appropriate post hoc attribution of backward-looking responsibility for unintended consequences, helping to avoid responsibility gaps and prevent similar events from repeating in the future. It also facilitates forward-looking responsibility by creating an incentive for the relevant humans to proactively reflect on the consequences of their decisions (design choices, operational control, interactions, etc.).\n\nBelow is an example code for the link between AI actions and human responsibility, obviously over-simplified for demonstration:\n\n
","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport matplotlib.pyplot as plt\n\nclass AI:\n def __init__(self):\n self.actions = [\"action1\", \"action2\", \"action3\"]\n\n def choose_action(self):\n # Placeholder logic to choose an action\n return np.random.choice(self.actions)\n\nclass Human:\n def __init__(self):\n self.responsibilities = {\n \"action1\": \"responsibility1\",\n \"action2\": \"responsibility2\",\n \"action3\": \"responsibility3\"\n }\n\n def evaluate_action(self, action):\n if action in self.responsibilities:\n return self.responsibilities[action]\n else:\n return \"Unknown responsibility\"\n\n# Instantiate AI and Human objects\nai = AI()\nhuman = Human()\n\n# Example AI action choice\naction_choice = \"2\"\naction_index = int(action_choice) - 1\n\nif action_index >= 0 and action_index < len(ai.actions):\n action = ai.actions[action_index]\nelse:\n print(\"Invalid action choice. Randomly selecting an action.\")\n action = ai.choose_action()\n\n# Human evaluates the action and determines the moral responsibility\nresponsibility = human.evaluate_action(action)\n\n# Print the results\nprint(\"AI Action:\", action)\nprint(\"Human Moral Responsibility:\", responsibility)\n\n# Update the action and responsibility lists for plotting\nactions = list(human.responsibilities.keys())\nresponsibilities = list(human.responsibilities.values())\n\n# Create a bar chart to visualize the action-responsibility links\nplt.bar(actions, responsibilities)\nplt.xlabel(\"AI Actions\")\nplt.ylabel(\"Human Moral Responsibilities\")\nplt.title(\"Action-Responsibility Links\")\nplt.show()","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2023-07-05T16:40:14.099286Z","iopub.execute_input":"2023-07-05T16:40:14.099803Z","iopub.status.idle":"2023-07-05T16:40:14.323495Z","shell.execute_reply.started":"2023-07-05T16:40:14.099770Z","shell.execute_reply":"2023-07-05T16:40:14.321618Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Conclusion**\n\nFor the purpose of summarizing the paper, Meaningful Human Control: Actionable Properties for AI System Development, some final points are made in achieving meaingful human control in AI-based systems:\n\n- Designing for meaningful human control requires designing for emergence\n\nThe socio-technical complexity of human-AI systems and the inherent uncertainty of some aspects of their operation call for designing for emergence ([Pendleton-Jullian, A.M, (2018)](https://doi.org/10.7551%2Fmitpress%2F11801.001.0001)), where the focus shifts to designing the social, physical, and technical infrastructures that jointly provide favorable conditions for interactions between agents to lead to emergence of desirable system properties and behaviors.\n- Meaningful human control is necessary but not sufficient for ethical AI\n\n**Meaningful human control does not prevent humans from consciously designing and operating the human-AI system in an unethical way.** Therefore, meaningful human control must be part of a larger set of design objectives that collectively align the human-AI system with societal values and norms.\n\n- Transdisciplinary practices are vital to achieve meaningful human control\n\n**While this is undoubtedly a challenge, it may prove to be a rewarding opportunity for socially inclusive innovation that puts human moral responsibility front and center.**\n\n## **Human-centered artificial intelligence in education: Seeing the invisible through the visible**\n\nContinuing with the thought of socially inclusive innovation that puts human moral responsibility front and center from the previous paper, the paper human-centered AI in Education, addresses research on the use of AI to evaluate new design methods and tools that can be leveraged to advance AI research, education, policy, and practice to improve human condition.\n\nAs smart learning environments must not only focus on performance, human feelings and outcomes should be the main concern. Smart learning analytics enables teachers to continually enhance educational content to tailor to students' level of understanding as they progress and monitor the performance of students so that teachers can then adapt their teaching. On the flip side, smart learning analytics also enables students to take control of their learning, know how they are performing in comparison with peers, and complete assessments to keep up with the learning progress of their peer group and help teachers to identify gaps in students' prerequisite knowledge and key study skills.\n\nSpecific to learning assessments, exploring the correlation between learning effectiveness and learning patterns would be key ([Wong, 2019](https://www.sciencedirect.com/science/article/pii/S0360131519301423)), and to achieve a high quality correlation, categorizing students' learning patterns and predicting their learning effectiveness would be necessary. Once the students' learning patterns are identified, timely counseling could be arranged. Additionally, students' motivation, attention, and engagement could also be enhanced through tailored learning activity designs. ([Huang et al., 2019](https://www.tandfonline.com/doi/abs/10.1080/10494820.2019.1636086?journalCode=nile20)) Below is a code example using UCI Machine Learning Repository's Student Performance [dataset](https://archive.ics.uci.edu/dataset/320/student+performance). By quantifying the contributing factors to a student's success as shown below, we would be better able to implement learning activity designs that focus on improving on the most important features that assists a student's learning.\n\n
","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import accuracy_score\nimport requests\nimport zipfile\nfrom io import BytesIO\n\n# Download the data\nurl = \"https://archive.ics.uci.edu/ml/machine-learning-databases/00320/student.zip\"\nresponse = requests.get(url)\n\n# Unzip the file and pull out the desired CSV, adjust the filename as needed\nzipfile.ZipFile(BytesIO(response.content)).extract('student-por.csv')\ndata = pd.read_csv('student-por.csv', sep=';')\n\n# Add a 'pass' column: 1 if 'G3' is 10 or more, 0 otherwise\ndata['pass'] = data['G3'].apply(lambda x: 1 if x >= 10 else 0)\n\n# Drop the original 'G3' column as well as other grade columns 'G1' and 'G2'\ndata = data.drop(['G1', 'G2', 'G3'], axis=1)\n\n# Convert categorical variables to dummy variables\ndata = pd.get_dummies(data, drop_first=True)\n\n# Split the data into training and test sets\nX = data.drop('pass', axis=1)\ny = data['pass']\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n\n# Train a Random Forest Classifier\nclf = RandomForestClassifier(random_state=42)\nclf.fit(X_train, y_train)\n\n# Predict the test set results\ny_pred = clf.predict(X_test)\n\n# Print the accuracy of the classifier\naccuracy = accuracy_score(y_test, y_pred)\nprint(f\"Accuracy: {accuracy * 100:.2f}%\")","metadata":{"execution":{"iopub.status.busy":"2023-07-05T16:11:52.121415Z","iopub.execute_input":"2023-07-05T16:11:52.122295Z","iopub.status.idle":"2023-07-05T16:11:53.302322Z","shell.execute_reply.started":"2023-07-05T16:11:52.122253Z","shell.execute_reply":"2023-07-05T16:11:53.300965Z"},"_kg_hide-input":true,"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n# Train a Random Forest Classifier\nclf = RandomForestClassifier(random_state=42)\nclf.fit(X_train, y_train)\n\n# Get importance\nimportance = clf.feature_importances_\n\n# Summarize feature importance\nfor i, j in enumerate(importance):\n print('Feature: %s, Score: %.5f' % (X.columns[i],j))\n\n# Plot feature importance\nplt.figure(figsize=(10,10))\nplt.barh([x for x in range(len(importance))], importance)\nplt.yticks([x for x in range(len(importance))], X.columns)\nplt.xlabel('Importance')\nplt.ylabel('Features')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-07-05T16:12:16.613192Z","iopub.execute_input":"2023-07-05T16:12:16.613628Z","iopub.status.idle":"2023-07-05T16:12:17.513580Z","shell.execute_reply.started":"2023-07-05T16:12:16.613598Z","shell.execute_reply":"2023-07-05T16:12:17.512593Z"},"_kg_hide-input":true,"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Some automation and AI-enabld intelligence for smart learning mentioned in the paper include the following:\n- AI-enabled conversational robot\n- AI-enabled personalization\n- Smart content, learning pathway, and recommendation\n- Automatic evaluations of students' learning outcome with grading policy\n- Intelligent assessment and evaluation\n- Automatic question generation\n- Automatic grading\n- AI-enabled plagiarism detection\n\nSmart assessment can be improved through increased evaluation of students' learning activities, such as preclass preview, reflection, oral reports, assignments, special topics, and program writing, and introduction of an examination mechanism into the smart evaluation system. ([Hsiao etal., 2019](https://www.tandfonline.com/doi/abs/10.1080/10494820.2018.1522651?journalCode=nile20))\n\nTeachers provide teaching materials, AI extracts the key concepts in texts through text summarization, and the system automatically generates test questions and refrence answers to evaluation the key concept. ([Kurdi et al., 2020](https://link.springer.com/article/10.1007/s40593-019-00186-y?utm_source=getftr&utm_medium=getftr&utm_campaign=getftr_pilot))\n\nThrough repeated testing and practice ([Stenlund et al., 2016](https://www.tandfonline.com/doi/abs/10.1080/01443410.2014.953037?journalCode=cedp20)), students can enhance their memory retention of the learned content, improve mastery of key concepts, and achieve better performance than if they had simply restudied the learning content.\n\n## **In Classrooms, Teachers Put A.I. Tutoring Bots to the Test**\n\nAccording to a New York Times article dated June 26, 2023, Newark public schools are cautiously trying out a new automated teaching aid from Khan Academy. Here's a teaching situation that involved the tutoring bot:\n\nOn a recent morning, Cheryl Drakeford, a third-grade teacher at First Avenue Elementary School in Newark, projected a challenging math question on her classroom’s whiteboard: “What fraction of the letters in the word MATHEMATICIAN are consonants?”\n\nMs. Drakeford knew that “consonant” might be an unfamiliar word to some students. So she suggested they ask Khanmigo, a new tutoring bot that uses artificial intelligence, for help.\n\nShe paused for a minute while about 15 schoolchildren dutifully typed the same question — “What are consonants?” — into their math software. Then she asked the third-graders to share the tutoring bot’s answer.\n\n“Consonants are the letters in the alphabet that are not vowels,” one student read aloud. “The vowels are A, E, I, O and U. Consonants are all the other letters.”\n\nThis kind of fast to the point answer was the first few issues encountered in a classroom learning setting. Other issues such as cost quickly piled up.\n\nSome messages left in the comments section also include the heavy use of technology during Covid, where the result was the lowest reading and math skills in a generation, mainly due to the lack of personal interactions in the education process.\n\nBelow is the full text of this article, for those who are interested in having a read:\n\n
\n\n \n \n \n In Classrooms, Teachers Put A.I. Tutoring Bots to the Test\n\n
\n\n## **Conclusion**\n\nIn the above essay, we have looked at:\n\nThe Three Actionable Principles for AI Policy:\n- Preliminary Landscape Assessment\n- Multi-Stakeholder Participation and Cross-Sectoral Feedback\n- Implementation and Operationalizability Support\n\nMeaningful Human Control: Actionable Properties for AI System Development\n- The human-AI system has an explicit moral operational design domain and the AI agent adheres to the boundaries of this domain\n- Human and AI Agents have appropriate and mutually compatible representations of the human-AI system and its context\n- The relevant humans and AI agents have ability and authority to control the system so that humans can act upon their responsibility\n- Actions of the AI agents are explicitly linked to actions of humans who are aware of their moral responsibility\n\nFollowing this human-centric approach to AI development, the paper Human-centered artificial intelligence in education: Seeing the invisible through the visible made specific technology suggestions to improving the learning experience of sudents. Specifically, it has suggested that establishing a high quality correlation through categorizing students' learning patterns and predicting their learning effectiveness is a vital first step in achieving an AI-assisted learning experience.\n\nTo close, I would like to use an excerpt from the third paper covered by this essay.\n\nThe movie \"The Imitation Game\" is mainly about the mutual imitation of humans and machines. The main character of the movie is Alan Turing, a crucial figure in cmputer science history. Alan Turing believed in the difference between humans and machines, particularly in terms of their modes of thinking. Alan Turing questioned whether the fact that a machine thinks differently from humans means that it does not think. As individuals, we may perceive those who think differently from us as \"not thinking\" and believe that others are wrong when their thought process differs from ours. Alan Turing famously said \"Sometimes it is the people no one can imagine anything of who do things no one can imagine.\"\n\nWith the machines doing unimaginable things, humans always have an awareness of potential dangers and can react with timely correction. As such, human-centered AI is based on human feelings and rethinks human reflective judgements. Humans are imperfect, and they should accept that the present version of themselves is the best, adjust their emotional state to feel the state of their soul, and develop an understanding of the invisible mind through the visible world.","metadata":{}},{"cell_type":"markdown","source":"### **References**\n\n1. AI recognition of patient race in medical imaging: a modelling study:\n https://www.thelancet.com/journals/landig/article/PIIS2589-7500(22)00063-2/fulltext\n\n2. Actionable Principles for Artificial Intelligence Policy: Three Pathways: \n https://link.springer.com/article/10.1007/s11948-020-00277-3\n\n3. Principled artificial intelligence: Mapping consensus in ethical and rights-based approaches to principles for AI:\n https://doi.org/https://doi.org/10.2139/ssrn.3518482\n\n4. Building trust through testing:\n https://cset.georgetown.edu/wp-content/uploads/Building-Trust-Through-Testing.pdf\n\n5. Toward trustworthy AI development: Mechanisms for supporting verifiable claims:\n http://arxiv.org/abs/2004.07213\n\n6. Estimating the brittleness of AI: Safety integrity levels and the need for testing out-of-distribution performance:\n http://arxiv.org/2009.00802\n\n7. The assessment list for trustworthy artificial intelligence (ALTAI):\n https://ec.europa.eu/digital-single-market/en/news/assessment-list-trustworthy-artificial-intelligence-altai-self-assessment\n\n8. Meaningful human control: actionable properties for AI system development: \n https://link.springer.com/article/10.1007/s43681-022-00167-3\n\n9. Coactive design: designing support for interdependence in joint activity:\n https://doi.org/10.5898/JHRI.3.1.Johnson\n\n10. Ecological interface design: theoretical foundations:\n https://doi.org/10.1109/21.156574\n\n11. Personalizing human-agent interaction through cognitive models:\n https://doi.org/10.3389/fpsyg.2020.561510\n\n12. Validating human driver models for interaction-aware automated vehicle controllers: A human factors approach:\n https://arxiv.org/abs/2109.13077\n \n13. Modular design patterns for hybrid learning and reasoning systems: a taxonomy, patterns and use cases:\n https://arxiv.org/abs/2102.11965\n\n14. The next decade in AI: four steps towards robust artificial intelligence:\n https://arxiv.org/abs/2002.06177\n\n15. A model for types and levels of human interaction with automation:\n https://ieeexplore.ieee.org/document/844354\n\n16. When Should We Use Care Robots? The Nature-of-Activities Approach:\n https://link.springer.com/article/10.1007/s11948-015-9715-4\n\n17. Value Sensitive Design: Shaping Technology with Moral Imagination:\n https://direct.mit.edu/books/book/4328/Value-Sensitive-DesignShaping-Technology-with\n\n18. Human behaviour with automated driving systems: a quantitative framework for meaningful human control:\n https://www.tandfonline.com/doi/full/10.1080/1463922X.2019.1574931\n\n19. Towards a dynamic balance between humans and automation: authority, ability, responsibility and control in shared and cooperative control situations:\n https://link.springer.com/article/10.1007/s10111-011-0191-6\n\n20. A human factors perspective on automated driving:\n https://www.tandfonline.com/doi/abs/10.1080/1463922X.2017.1293187?journalCode=ttie20\n\n21. Translating Values into Design Requirements:\n https://link.springer.com/chapter/10.1007/978-94-007-7762-0_20\n \n22. Meaningful human control as reason-responsiveness: the case of dual-mode vehicles:\n https://link.springer.com/article/10.1007/s10676-019-09519-w\n\n23. Design Unbound: Designing for Emergence in a White Water World: Ecologies of Change\n https://direct.mit.edu/books/book/4151/Design-Unbound-Designing-for-Emergence-in-a-White\n \n24. Human-centered artificial intelligence in education: Seeing the invisible through the visible\n https://www.sciencedirect.com/science/article/pii/S2666920X21000023\n\n25. Exploring sequences of learner activities in relation to self-regulated learning in a massive open online course\n https://www.sciencedirect.com/science/article/pii/S0360131519301423\n\n26. Exploring the effects of online learning behaviors on short-term and long-term learning outcomes in flipped classrooms\n https://www.tandfonline.com/doi/abs/10.1080/10494820.2018.1522651?journalCode=nile20\n \n27. A systematic review of automatic question generation for educational purposes\n https://link.springer.com/article/10.1007/s40593-019-00186-y?utm_source=getftr&utm_medium=getftr&utm_campaign=getftr_pilot\n\n28. Effects of repeated testing on short- and long-term memory performance across different test formats\n https://www.tandfonline.com/doi/abs/10.1080/01443410.2014.953037?journalCode=cedp20","metadata":{}},{"cell_type":"markdown","source":"**Submission**","metadata":{}},{"cell_type":"code","source":"import pandas as pd\ndf = pd.read_csv('/kaggle/input/2023-kaggle-ai-report/sample_submission.csv')\ndf.iloc[0,1] = 'AI ethics'\ndf.iloc[1,1] = 'https://www.kaggle.com/code/luckypen/actionable-ai-ethics'\ndf.iloc[2,1] = 'https://www.kaggle.com/code/asenath/on-ethics-and-ai/comments#2330488'\ndf.iloc[3,1] = 'https://www.kaggle.com/code/danielanewton/ethics-ai-and-the-law/comments#2330531'\ndf.iloc[4,1] = 'https://www.kaggle.com/code/jotangwq/ai-ethics-through-the-lens-of-immanuel-kant/comments#2330566'\ndf.to_csv('submission.csv', index=False)\ndf.head()","metadata":{},"execution_count":null,"outputs":[]}]}
![](\"https://www.science.org/cms/10.1126/science.aax2342/asset/1353fece-9d19-4293-be71-0d7e8a834b28/assets/graphic/366_447_f1.jpeg\")
\n \n ![](\"https://duet-cdn.vox-cdn.com/thumbor/0x0:2040x1360/1080x720/filters:focal(1020x680:1021x681):format(webp)/cdn.vox-cdn.com/uploads/chorus_asset/file/10465661/wjoel_180320_2353_healthcare_001.jpg\")
\n \n ![](\"https://www.thelancet.com/cms/attachment/33fcdd07-e243-49d9-bd1e-904779ac0974/gr1.jpg\")
\n \n ![](\"https://aiindex.stanford.edu/wp-content/uploads/2023/04/fig_3.2.1_num_AI_incidents_controversies-scaled.jpg\")
\n \n ![](\"https://cdn.wionews.com/sites/default/files/styles/story_page/public/2023/07/08/365416-weekend-banner-3.jpg?imwidth=1920\")
\n \n ![](\"https://imageio.forbes.com/specials-images/imageserve/62e0112673b5688ca62ace28/Explainable-Artificial-Intelligence--XAI-/960x0.jpg?format=jpg&width=960\")
\n \n ![](\"https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe2f5012f-1ec1-4d3c-a0e2-07c6c83adf9b_562x455.png\")
\n \n ![](\"https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8ece3053-eaec-43b3-9dca-040c478be051_576x455.png\")
\n \n ![](\"https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F39733a4e-c954-40ea-b324-752f2f74bce2_1026x256.png\")
\n \n ![](\"https://www.diu.mil/images/diu.png\")
\n \n ![](\"https://media.springernature.com/full/springer-static/image/art%3A10.1007%2Fs43681-022-00167-3/MediaObjects/43681_2022_167_Fig1_HTML.png\")
\n ![](\"https://static01.nyt.com/images/2023/06/15/multimedia/AI-classrooms-1-03-jpch/AI-classrooms-1-03-jpch-superJumbo.jpg?quality=75&auto=webp\")
\n \n