![\"\"](\"http://i.imgur.com/F255rFT.png\")
You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.
\n\n Privately sharing code or data outside of teams is not permitted.\n It's okay to share code if made available to all participants on the forums.\n
\nTeam mergers are not allowed in this competition.
\n\nYou may work in teams up to size 2.
\nYou may submit a maximum of 20 entries per day.
\nYou may select up to 5 final submissions for judging.
\nStart Date: TBA
\nMerger Deadline: None
\nEntry Deadline: None
\nEnd Date: 2/1/2014 12:00 AM UTC
\n\t\nYou are strongly encouraged to work in a group of two students
\nGroups may not collaborate with other groups. You cannot cite other team's work. This includes sharing data, intermediate and final results, writing, or discussing your detailed method with other groups. You may not view reports from other teams until after the peer-review phase begins.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "The format of the exam is a mock peer-reviewed conference. You will develop an algorithm, prepare a professional paper, submit an anonymized version to the peer review system (details about this to be provided soon!), and peer-review the work from other groups. There are three deliverables:
\nYou and your team of two Cornell Tech students are surely on the path to fame and fortune! You have been recruited by Google to disrupt Google Image Search by building a better search engine using novel statistical learning techniques.
\nThe specifications are simple: We need a way to search for relevant images given a natural language query. For instance, if a user types \"dog jumping to catch frisbee,\" your system will rank-order the most relevant images from a large database.
\nHere are some details:
\nUse all of your skills, tools, and experience. It is OK to use libraries like numpy, scikit-learn, pandas, etc., as long as you cite them. Use cross-validation on training set to debug your algorithm. Submit your results to the Kaggle leaderboard and send your complete writeup to EasyChair. The data you use --- and the way you use the data --- is completely up to you.
\nThe best teams (of two Cornell Tech students, recall) might use visualization techniques for debugging (e.g., show top images retrieved by your algorithm and see whether they make sense or not), preprocessing, a nice way to compare tags and descriptions, leveraging visual features and combining them with tags and descriptions, supervised and/or unsupervised learning to best understand how to best take advantage of each data source available to them.
\nThe best reports will be professionally written. We suggest including an Abstract, followed by an Introduction section including motivations of your method and a detailed description of each step in your pipeline / framework you used for this task. Then, include a detailed Experiment section and a Results section. If time permits, a Background / Related Work section can help to point out the relevant work in the image retrieval literature.
\nThe best reports use a professional style adopted by a major academic conference. NIPS is a good choice. Teams can download a template from Section 4 Paper Format of the NIPS Author Guidelines. We recommend you to use the LaTeX template, but this is not a requirement. If you're more familiar with Word, use Word.
\nThe best peer reviews will be detailed and thorough, pointing out potential areas of improvement as well as complimenting their peers' strengths.
\nThe best teams understand how to divide the precious time and energy among all members of the group. They might split into roles, preventing programming students from messing up the writing and ensuring writing gurus don't screw up the code. Close contact is always maintained within top-performing teams. When hardship happens within the best teams, blame is not assigned---it is overcome.
\nMay the best team win!
\nYou are strongly encouraged to work in a group of two students.
\nGroups may not collaborate with other groups. You cannot cite other teams' work. This includes sharing data, intermediate and final results, writing, or discussing your detailed method with other groups. You may not view reports from other teams until after the peer-review phase begins!
\nThe \"Peer Review\" phase will be double-blind. This means authors will not know who the reviewers are, and the reviewers should not know who the authors are. This protects both sides.
\nTo maintain anonymity, don't include team member names in the actual paper that you submit to Dropbox!
\nHowever, we need to know who you are. So please use the following file name:\n TeamNameOnKaggle_Author1lastname_Author2lastname_report.pdf\n This will be hidden from your reviewers.
See the following resources for tips on how to write a professional review:
\nThe evaluation metric is Mean Average Precision at 20 (MAP@20) on the test set. A good explanation of the metric can be found here.
\n\nIn our case, there is only one true corresponding image. So for a description, suppose your algorithm finds the corresponding image in the list of top 20 images you return, and is ranked i-th. Then MAP@20 gives a score of:
\n\n\\[ score = \\frac{1}{i} \\]
\n\nFor example, if it's ranked 1st you get a score of 1, if it's ranked 2nd you get a score of 0.5, if it's ranked 3rd you get a score of 0.333, if it's ranked 20th you get a score of 0.05, etc. If the corresponding image isn't in your list of top 20 images you get a score of 0. The overall score is calculated as the average score on the test set.
\n\nWe divide the test set into two splits: a public split and a private split. Results on the Leaderboard are evaluated on the public split and the private split is used for grading.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }