{"id":16214835,"url":"https://github.com/lecrapouille/chessneuneu","last_synced_at":"2026-02-21T09:32:14.570Z","repository":{"id":115856939,"uuid":"117305157","full_name":"Lecrapouille/ChessNeuNeu","owner":"Lecrapouille","description":"[Application][Version 0.1][Functional][WIP] Non serious chess engine self learning chess rules (legal moves)","archived":false,"fork":false,"pushed_at":"2022-11-09T01:44:22.000Z","size":5747,"stargazers_count":4,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-03T01:33:59.921Z","etag":null,"topics":["chess","chess-engine","cpp","neural-network","sfml2"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Lecrapouille.png","metadata":{"files":{"readme":"README.md","changelog":"ChangeLog","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":"AUTHORS","dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-01-13T01:52:59.000Z","updated_at":"2023-04-08T10:56:50.000Z","dependencies_parsed_at":null,"dependency_job_id":"a01f17e5-02e2-4c57-adda-ee4fa924a4b8","html_url":"https://github.com/Lecrapouille/ChessNeuNeu","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/Lecrapouille/ChessNeuNeu","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lecrapouille%2FChessNeuNeu","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lecrapouille%2FChessNeuNeu/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lecrapouille%2FChessNeuNeu/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lecrapouille%2FChessNeuNeu/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Lecrapouille","download_url":"https://codeload.github.com/Lecrapouille/ChessNeuNeu/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lecrapouille%2FChessNeuNeu/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29678236,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-21T06:23:40.028Z","status":"ssl_error","status_checked_at":"2026-02-21T06:23:39.222Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["chess","chess-engine","cpp","neural-network","sfml2"],"created_at":"2024-10-10T11:13:08.981Z","updated_at":"2026-02-21T09:32:14.541Z","avatar_url":"https://github.com/Lecrapouille.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ChessNeuNeu\n\nNot an effective chess engine but just a brainstorming/proof of concept\nproject for understanding how deep learning (such as neural network (NN)\nor convolution neural network (CNN)) can learn chess rules and understand\nchess movements without cheating.\n\nThis project has started after the reading of this article:\nhttps://www.futura-sciences.com/tech/actualites/technologie-alphazero-ia-google-deepmind-devient-imbattable-echecs-61409/\nwhich make us interrogate on how well machine learning can understand chess\nstrategies, what filters/patterns they really learnt for evaluating\nthe chessboard (cost function used in minimax/alphabeta pruning). It's\nvery difficult to evaluate what IA have really learnt. We know that\nneural network can have errors, biases ... and for evalutating a\nchessboard position, even if the machine does 10-30% of errors when\nselecting the best move, it will difficult for a human to prove it\nespecially with IA having such a huge ELO levels.\n\nTo simplify the problem, we can start asking us if a machine can simply\nlearn by themselves chess rules. I guess that in AlphaZero chess rules\nare hardcoded and the deep learning improved minimax/alphabeta pruning.\nIn other [https://github.com/ashudeep/ConvChess](projects) the machine can\npredict the chess movements but have around 1% error on learning rules.\nIn this case even a 1% error is not acceptable because cheating when moving\nits pieces is forbidden.\n\nIn addition, knowing that smallest chess engines have 100 lines of codes\nof C or Python (including board evaluation) like\n[https://github.com/thomasahle/sunfish](sunfish), it is interesting to know\nhow fastidious (in term of memory for storing the CNN, in term of\ntraining iterations) it is to create a neural network doing the\nequivalent of 100 lines of code. Finaly a question could be: is it\npossible to generate this 100 lines of code from what have learnt the\nneural network ?\n\n## Table of Contents\n\n* [How to compile the project](https://github.com/Lecrapouille/LEchecDeNeuneu/blob/master/doc/Compilation.md).\n* [Command-Line](https://github.com/Lecrapouille/LEchecDeNeuneu/blob/master/doc/CommandLine.md).\n* [Project features](https://github.com/Lecrapouille/LEchecDeNeuneu/blob/master/doc/ProjectFeatures.md).\n* [Software Architecture](https://github.com/Lecrapouille/LEchecDeNeuneu/blob/master/doc/SoftwareArchitecture.md).\n* [Chess Algebra](https://github.com/Lecrapouille/LEchecDeNeuneu/blob/master/doc/ChessAlgebra-fr.pdf). In french for the moment.\n* [Machine Learning Algorithms](https://github.com/Lecrapouille/LEchecDeNeuneu/blob/master/doc/MachineLearning-en.pdf). Work in progress.\n* [Credits](https://github.com/Lecrapouille/LEchecDeNeuneu/blob/master/doc/Credits.md).\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flecrapouille%2Fchessneuneu","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flecrapouille%2Fchessneuneu","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flecrapouille%2Fchessneuneu/lists"}