{"id":13653528,"url":"https://github.com/gdb/kaggle","last_synced_at":"2026-01-20T18:21:29.073Z","repository":{"id":34459903,"uuid":"38395872","full_name":"gdb/kaggle","owner":"gdb","description":"A collection of Kaggle solutions. Not very polished.","archived":false,"fork":false,"pushed_at":"2018-10-01T19:29:21.000Z","size":995,"stargazers_count":757,"open_issues_count":0,"forks_count":137,"subscribers_count":43,"default_branch":"master","last_synced_at":"2024-11-10T04:38:27.675Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/gdb.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2015-07-01T21:24:54.000Z","updated_at":"2024-11-02T09:01:42.000Z","dependencies_parsed_at":"2022-07-28T21:08:58.010Z","dependency_job_id":null,"html_url":"https://github.com/gdb/kaggle","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gdb%2Fkaggle","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gdb%2Fkaggle/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gdb%2Fkaggle/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gdb%2Fkaggle/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gdb","download_url":"https://codeload.github.com/gdb/kaggle/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250385141,"owners_count":21421863,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":[],"created_at":"2024-08-02T02:01:12.167Z","updated_at":"2026-01-20T18:21:29.059Z","avatar_url":"https://github.com/gdb.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Kaggle solutions\n\nI've been using Kaggle as an excuse to learn techniques in machine\nlearning/artificial intelligence.\n\n## Resources I've been learning from\n\nHere are some primary resources I've been learning from (in rough\nchronological order). For reference, I started from an extensive\nprogramming background, a decent but rusty math background, and a\nrudimentary background in machine learning.\n\n- http://karpathy.github.io/2015/05/21/rnn-effectiveness/: It was fun\n  to play with the released code, even though I didn't yet know what\n  many of the parameters meant.\n\n- http://www.pyimagesearch.com/2014/09/22/getting-started-deep-learning-python/:\n  Didn't worry too much about the details of Deep Belief Networks,\n  since I've been told those aren't behind the most recent advances in\n  deep learning. However, I found a lot of value in actually getting a\n  not-completely-black-boxed neural network up and running.\n\n- http://neuralnetworksanddeeplearning.com/: It wasn't until I worked\n  through this book that I really felt like I understood what was\n  going on (or at least knew enough to have a sense of what I didn't\n  know). I highly recommend going through the entire thing. I was\n  particularly impressed by the author's ability to anticipate my\n  confusions and objections, and also convey intuitions and\n  motivations.\n\n- https://class.coursera.org/ml-005/lecture: Andrew Ng's Machine\n  Learning course. Contains helpful details on a number of topics I\n  hadn't seen before. However, the course moves slower than I was\n  hoping, but with the right cherry-picking it felt pretty useful.\n\n- http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf: Useful for\n  learning some practical tricks for getting better performance out of\n  your neural network. The first half is very useful and readable\n  (though I didn't work through all of the math). The second half\n  seems less so: as they conclude the paper, \"Classical second-order\n  methods are impractical in almost all useful cases\".\n\n- http://deeplearning.net/tutorial/lenet.html: Decent introduction to\n  convolutional neural networks. I wasn't previously familiar with\n  convolutions and didn't fully understand it until I'd read\n  http://www.songho.ca/dsp/convolution/convolution.html.\n\n- http://www.cs.utoronto.ca/~ilya/pubs/ilya_sutskever_phd_thesis.pdf:\n  Contains thorough background on recurrent neural networks, with many\n  experiments and tricks for training your own.\n\n- http://andrew.gibiansky.com/blog/machine-learning/conjugate-gradient/:\n  This whole blog is great. It has good exposition on some of the more\n  mathematically-involved techniques.\n\n- http://arxiv.org/pdf/1211.5063v2.pdf: A better choice of activation\nfunction and initialization scheme.\n\n- http://deepdish.io/2015/02/24/network-initialization/: More recent\n  overview of initialization techniques.\n\n- http://yyue.blogspot.com/2015/01/a-brief-overview-of-deep-learning.html:\n  Great overview of how to think about deep neural networks, and how\n  to train them in practice.\n\n- https://christopherolah.wordpress.com/: Many amazing blog posts\n  which explore deep concepts in accessible ways.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgdb%2Fkaggle","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgdb%2Fkaggle","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgdb%2Fkaggle/lists"}