{"id":23257327,"url":"https://github.com/turiphro/deeplearning","last_synced_at":"2025-10-08T13:18:54.403Z","repository":{"id":91914717,"uuid":"66830000","full_name":"turiphro/deeplearning","owner":"turiphro","description":"Deep Learning track / hackdays","archived":false,"fork":false,"pushed_at":"2017-10-28T22:54:13.000Z","size":10944,"stargazers_count":7,"open_issues_count":0,"forks_count":3,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-08-20T14:45:51.731Z","etag":null,"topics":["computer-vision","deep-dreaming","deep-learning","deep-neural-networks","deeplearning","deepmind","machine-learning","neural-network","papers","reading-group","reinforcement-learning","study-group","tensorflow"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/turiphro.png","metadata":{"files":{"readme":"README.md","changelog":null,"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":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2016-08-29T09:26:49.000Z","updated_at":"2022-06-13T04:15:37.000Z","dependencies_parsed_at":"2023-04-22T04:15:11.201Z","dependency_job_id":null,"html_url":"https://github.com/turiphro/deeplearning","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/turiphro/deeplearning","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/turiphro%2Fdeeplearning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/turiphro%2Fdeeplearning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/turiphro%2Fdeeplearning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/turiphro%2Fdeeplearning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/turiphro","download_url":"https://codeload.github.com/turiphro/deeplearning/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/turiphro%2Fdeeplearning/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278949625,"owners_count":26074068,"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","status":"online","status_checked_at":"2025-10-08T02:00:06.501Z","response_time":56,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["computer-vision","deep-dreaming","deep-learning","deep-neural-networks","deeplearning","deepmind","machine-learning","neural-network","papers","reading-group","reinforcement-learning","study-group","tensorflow"],"created_at":"2024-12-19T12:28:37.449Z","updated_at":"2025-10-08T13:18:54.396Z","avatar_url":"https://github.com/turiphro.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"deeplearning\n============\nWe're doing a biweekly study group about **Deep Learning** in Amsterdam: 1 evening (2-3h) every other week. It's for a group of people with strong CS + LA background, pref. some familiarity with machine learning and neural network basics.\n\n\nSyllabus\n--------\n| Session  | Date         | Theory                  | Coding                       |\n| -------- | ------------ | ----------------------- | ---------------------------- |\n| *week 1* | *2016-09-18* | *intro talk, NN\u0026DL ch1* | *ch1 coding assignments*     |\n| *week 2* | *2016-10-02* | *NN\u0026DL^ ch2*            | *webcam demo*                |\n| *week 3* | *2016-10-16* | *NN\u0026DL^ ch3*            | *sk-learn neural nets*       |\n| *week 4* | *2016-10-30* | *NN\u0026DL^ ch4 + ch5*      | *intro TensorFlow*           |\n| *week 5* | *2016-11-13* | *NN\u0026DL^ ch6*            | *TensorFlow (part 2)*        |\n| *week 6* | *2016-11-27* | *discussion*            | *TensorFlow (projects)*      |\n| *week 7* | *2016-12-11* | *DL$ ch10, RNNs, papers*| *TensorFlow (projects)*      |\n| *week 8* | *2016-12-25* | *(skip)*                |                              |\n| *week 9* | *2017-01-08* | *DL$ ch11, papers*      | *run existing projects*      |\n| *week 10* | *2017-01-22* | *DL$ ch12 (apps), papers* | *Projects show-off, cocktails* |\n\n^ [book] Neural Networks and Deep Learning, by Michael Nielsen\n\n$ [book] Deep Learning, by Goodfellow, Bengio and Courville ([full reading notes](deeplearningbook_notes.md))\n\n\n## Resources\nsyllabus, proposal: practical approach, but with deep understanding (not just trying github repos): book Nielsen (ML -\u003e DL), then a course (either Google, creative DL, or (outdated) coursera) with corresponding homeworks. Extra: papers (DL classics, microsoft ebook, IBM watson, DeepMind), practical DL projects (TensorFlow, Theano, Torch, Keras.io), deep dreaming, GPU programming\n\n- [book] by Michael Nielsen:\n  http://neuralnetworksanddeeplearning.com/chap1.html\n- [book] upcoming, view online:\n  http://www.deeplearningbook.org\n- [course] UvA, Max Welling:\n  https://uvadlc.github.io/ in Torch -\u003e also lists 'similar courses'\n- [course] by Hinton (2012):\n  https://www.coursera.org/course/neuralnets, supposedly outdated algorithms (in apr 2016)\n- [course] Deep Learning (TensorFlow, by Google):\n  https://www.udacity.com/course/deep-learning--ud730 (part of nanodegree ML)\n- [course] Deep Learning \u0026 creative applications [2016]:\n  https://www.kadenze.com/courses/creative-applications-of-deep-learning-with-tensorflow/info\n- [blogpost] Demystifying Deep Reinforcement Learning [2015]:\n  https://www.nervanasys.com/demystifying-deep-reinforcement-learning/\n- [video lectures] RL Course by David Silver [2015]:\n  https://www.youtube.com/watch?v=2pWv7GOvuf0\n- [blogpost series] RL + DNNs in TensorFlow [2016], multiple posts:\n  https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-0-q-learning-with-tables-and-neural-networks-d195264329d0#.967pe8962\n- [blogpost] Differentiable neural computers [2016]:\n  https://deepmind.com/blog/differentiable-neural-computers/\n  (With link to paper behind paywall)\n- [blogpost] RNNs: The Unreasonable Effectiveness of Recurrent Neural Networks [2015]\n  http://karpathy.github.io/2015/05/21/rnn-effectiveness/\n\n\n## Papers\n\n- how it started: [Hinton 2006](http://www.cs.toronto.edu/~fritz/absps/ncfast.pdf): deep belief networks\n- DeepMind \u0026 Google papers: [Atari](https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf), [AlphaGo](http://airesearch.com/wp-content/uploads/2016/01/deepmind-mastering-go.pdf), [WaveNet](https://arxiv.org/pdf/1609.03499.pdf)), Building High-level Features Using Large Scale Unsupervised Learning (\"Youtube paper\"), Vincent Vanhoucke 2012-2015 (\"Android papers\")\n- Watson ([Building Watson](https://www.aaai.org/ojs/index.php/aimagazine/article/download/2303/2165), [many other papers](http://researcher.watson.ibm.com/researcher/view_group_pubs.php?grp=2099)): various techniques combined\n- Turing machine (2014 RNN python output predictor, [2014 Neural Turing Machines](https://arxiv.org/pdf/1410.5401v2.pdf))\n- more recent: ICCV 2015 CNN examples http://www.computervisionblog.com/2015/12/iccv-2015-twenty-one-hottest-research.html; more examples in these slide decks: SLAM \u0026 geometry, Depth vision \u0026 geometry, etc\n- your favourite paper!\n\n\n## Software libraries\n\n- theano (Python) paper [4p] http://biglearn.org/2011/files/papers/biglearn2011_submission_18.pdf\n\n- torch (Lua; Facebook/FAIR contribs; used by Google) paper [5p] http://publications.idiap.ch/downloads/reports/2002/rr02-46.pdf\n\n- TensorFlow (python/c++) by Google http://www.tensorflow.org\n\n- Keras.io High-level Python library using theano and tensorflow, also CV\n\n- Caffe http://caffe.berkeleyvision.org/\n\n\n## Datasets\n\n**Images**\n- MNIST (60k hand-written digits; 28x28px) http://yann.lecun.com/exdb/mnist/\n- CIFAR-10/CIFAR-100 (60k, 10/100 classes; 32x32pxRGB) http://www.cs.toronto.edu/%7Ekriz/cifar.html\n- SVHN public Street View House Numbers (600k; box+label per digit) http://ufldl.stanford.edu/housenumbers/\n- Image-net (16M, 20k classes) or subset ILSVRC (3M; 1000 classes) http://image-net.org/\n- NYU depth v2 (fixed scenes) http://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html\n- KITTI (data from car driving) http://www.cvlibs.net/datasets/kitti/ (have more code and datasets)\n- more datasets: http://www.cvlibs.net/links.php?page=Main+page\n\n**Language**\n- Amazon Reviews (35M; 2015) https://snap.stanford.edu/data/web-Amazon.html\n- Movielens (20M) http://grouplens.org/datasets/movielens/\n- WordNet, per language http://www.certifiedchinesetranslation.com/openaccess/WordNet/\n- Google Books n-grams (2TB of txt) https://storage.googleapis.com/books/ngrams/books/datasetsv2.html\n- TIMIT acoustic corpus https://catalog.ldc.upenn.edu/ldc93s1\n- NetFlix Price (recommender systems) http://academictorrents.com/details/9b13183dc4d60676b773c9e2cd6de5e5542cee9a\n\n**Other**\n- Kaggle datasets https://www.kaggle.com/datasets\n- AWS datasets overview https://aws.amazon.com/datasets/\n- EU open datasets https://data.europa.eu/euodp/en/data\n- Wikipedia listing per data type https://en.wikipedia.org/wiki/List_of_datasets_for_machine_learning_research\n\n\n## Ideas for Projects\n\n- self-learning Mario or Atari games;\n  homebrew: https://www.youtube.com/watch?v=qv6UVOQ0F44; DeepMind: https://www.youtube.com/watch?v=V1eYniJ0Rnk, paper https://arxiv.org/pdf/1312.5602v1.pdf\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fturiphro%2Fdeeplearning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fturiphro%2Fdeeplearning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fturiphro%2Fdeeplearning/lists"}