##ENTRY IN THIS COMPETITION CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL COMPETITION RULES. *The ConCon Challenge is a skills-based competition to promote and further the field of machine learning. You must register via the Competition Website to enter . To enter the Competition, you must agree to these Official Competition Rules, which incorporate by reference the provisions and content of the Competition Website and any Specific Competition Rules herein (collectively, the "Rules"). Please read these Rules carefully before entry to ensure you understand and agree. You further agree that Submission in the Competition constitutes agreement to these Rules. You may not submit to the Competition and are not eligible to receive the prizes associated with this Competition unless you agree to these Rules. These Rules form a binding legal agreement between you and the Competition Sponsor with respect to the Competition. Your competition Submissions must conform to the requirements stated on the Competition Website. Your Submissions will be scored based on the evaluation metric described on the Competition Website, and the novelty. Subject to compliance with the Competition Rules, Prizes, if any, will be awarded to Participants with the best scores, based on the merits of the data science models submitted. See below for the complete Competition Rules.* **You cannot sign up to Kaggle from multiple accounts and therefore you cannot enter or submit from multiple accounts.** ###COMPETITION-SPECIFIC RULES In addition to the provisions of the General Competition Rules below, you understand and agree to these Competition-Specific Rules. ####1. TEAM LIMITS a. The maximum Team size is 5. b. Team mergers are allowed and can be performed by the Team leader. In order to merge, the combined Team must have a total Submission count less than or equal to the maximum allowed as of the Team Merger Deadline. The maximum allowed is the number of Submissions per day multiplied by the number of days the competition has been running. ####2. SUBMISSION LIMITS a. You may submit a maximum of **10 Submissions** per day. b. You may select up to **3 Final Submissions** for judging. ####3. COMPETITION TIMELINE a. Competition Timeline dates (including Entry Deadline, Final Submission Deadline, Start Date, and Team Merger Deadline, as applicable) are reflected on the competition’s Overview > Timeline page. ####4. COMPETITION DATA ACCESS AND USE The dataset is made available under the BSD 2-Clause "Simplified" License (see https://opensource.org/license/bsd-2-clause) ####5. TRAINING INSTRUCTIONS - You must train on only one of the variants (**disjoint** or **strict**) and test on **unconf** for submission - Training should be conducted one step at a time, following the continual learning order given by the dataset. This means a model should first be trained on data from Task 0, then updated using data from Task 1, and after that, updated using data from Task 2. - Data used to train and update the model may not simply be accumulated fully, however using a small amount of memory as a memory buffer is in principle permitted. The size of the buffer should be justified and generally as small as possible. ####6. AUXILIARY INFORMATION You are required to submit a readme file along with any submission. The template for the readme file is as follows: #####readme File ```markdown ABSTRACT Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nunc ut lectus nisl. Sed posuere odio quis nibh aliquam, non fringilla risus fringilla. Sed non enim in ante molestie gravida. Sed rhoncus vel felis non varius. Aliquam et posuere turpis. Lorem ipsum dolor sit amet, consectetur adipiscing elit. Donec eget iaculis orci, id tincidunt elit. Donec velit massa, lobortis non dignissim id, accumsan a sem. Etiam quis purus a tortor faucibus pulvinar vitae a est. DATASET USED IN TRAINING: Choose from either "Strict" or "Disjoint" (Only one is allowed) BUFFER SIZE: Applicable only if the methodology involves the use of a replay buffer. ADDITIONAL COMMENTS: Optional, if any. ``` In addition to the solutions submission and the readme file, you are required to provide a detailed report of how the submission was generated. This may include a detailed description of methodology, where one must be able to reproduce the approach by reading the description, and includes a detailed explanation of the architecture, preprocessing, loss function, training details, hyper-parameters, etc. The description should also include a link to a code repository with complete and detailed instructions so that the results obtained can be reproduced. In the event that the results are not reproducible within a reasonable margin of error, the entry will be disqualified.