[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-9666":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":41,"readmeContent":42,"aiSummary":43,"trendingCount":16,"starSnapshotCount":16,"syncStatus":18,"lastSyncTime":44,"discoverSource":45},9666,"mit-deep-learning","lexfridman\u002Fmit-deep-learning","lexfridman","Tutorials, assignments, and competitions for MIT Deep Learning related courses.","https:\u002F\u002Fdeeplearning.mit.edu",null,"Jupyter Notebook",10444,2203,630,6,0,1,2,10,4,45,"MIT License",false,"master",true,[27,28,29,30,31,32,33,34,35,36,37,38,39,40],"artificial-intelligence","data-science","deep-learning","deep-reinforcement-learning","deep-rl","deeplearning","jupyter-notebooks","machine-learning","mit","neural-networks","segmentation","self-driving-cars","tensorflow","tensorflow-tutorials","2026-06-12 02:02:10","# MIT Deep Learning\n\n\u003Ca href=\"https:\u002F\u002Fdeeplearning.mit.edu\u002F\">\u003Cimg src=\"https:\u002F\u002Fdeeplearning.mit.edu\u002Ffiles\u002Fimages\u002Fmit_deep_learning.png\">\u003C\u002Fa>\n\nThis repository is a collection of tutorials for [MIT Deep Learning](https:\u002F\u002Fdeeplearning.mit.edu\u002F) courses. More added as courses progress.\n\n## Tutorial: Deep Learning Basics\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flexfridman\u002Fmit-deep-learning\u002Fblob\u002Fmaster\u002Ftutorial_deep_learning_basics\u002Fdeep_learning_basics.ipynb\">\u003Cimg src=\"https:\u002F\u002Fi.imgur.com\u002Fj4FqBuR.gif\">\u003C\u002Fa>\n\nThis tutorial accompanies the [lecture on Deep Learning Basics](https:\u002F\u002Fwww.youtube.com\u002Fwatch?list=PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf&v=O5xeyoRL95U). It presents several concepts in deep learning, demonstrating the first two (feed forward and convolutional neural networks) and providing pointers to tutorials on the others. This is a good place to start.\n\nLinks: \\[ [Jupyter Notebook](https:\u002F\u002Fgithub.com\u002Flexfridman\u002Fmit-deep-learning\u002Fblob\u002Fmaster\u002Ftutorial_deep_learning_basics\u002Fdeep_learning_basics.ipynb) \\]\n\\[ [Google Colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Flexfridman\u002Fmit-deep-learning\u002Fblob\u002Fmaster\u002Ftutorial_deep_learning_basics\u002Fdeep_learning_basics.ipynb) \\]\n\\[ [Blog Post](https:\u002F\u002Fmedium.com\u002Ftensorflow\u002Fmit-deep-learning-basics-introduction-and-overview-with-tensorflow-355bcd26baf0) \\]\n\\[ [Lecture Video](https:\u002F\u002Fwww.youtube.com\u002Fwatch?list=PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf&v=O5xeyoRL95U) \\]\n\n\n## Tutorial: Driving Scene Segmentation\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flexfridman\u002Fmit-deep-learning\u002Fblob\u002Fmaster\u002Ftutorial_driving_scene_segmentation\u002Ftutorial_driving_scene_segmentation.ipynb\">\u003Cimg src=\"images\u002Fthumb_driving_scene_segmentation.gif\">\u003C\u002Fa>\n\nThis tutorial demostrates semantic segmentation with a state-of-the-art model (DeepLab) on a sample video from the MIT Driving Scene Segmentation Dataset.\n\nLinks: \\[ [Jupyter Notebook](https:\u002F\u002Fgithub.com\u002Flexfridman\u002Fmit-deep-learning\u002Fblob\u002Fmaster\u002Ftutorial_driving_scene_segmentation\u002Ftutorial_driving_scene_segmentation.ipynb) \\]\n\\[ [Google Colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Flexfridman\u002Fmit-deep-learning\u002Fblob\u002Fmaster\u002Ftutorial_driving_scene_segmentation\u002Ftutorial_driving_scene_segmentation.ipynb) \\]\n\n## Tutorial: Generative Adversarial Networks (GANs)\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flexfridman\u002Fmit-deep-learning\u002Fblob\u002Fmaster\u002Ftutorial_gans\u002Ftutorial_gans.ipynb\">\u003Cimg src=\"images\u002Fthumb_mushroom_biggan.gif\">\u003C\u002Fa>\n\nThis tutorial explores generative adversarial networks (GANs) starting with BigGAN, the state-of-the-art conditional GAN.\n\nLinks: \\[ [Jupyter Notebook](https:\u002F\u002Fgithub.com\u002Flexfridman\u002Fmit-deep-learning\u002Fblob\u002Fmaster\u002Ftutorial_gans\u002Ftutorial_gans.ipynb) \\]\n\\[ [Google Colab](https:\u002F\u002Fcolab.research.google.com\u002Fgithub\u002Flexfridman\u002Fmit-deep-learning\u002Fblob\u002Fmaster\u002Ftutorial_gans\u002Ftutorial_gans.ipynb) \\]\n\n## DeepTraffic Deep Reinforcement Learning Competition\n\n\u003Ca href=\"https:\u002F\u002Fselfdrivingcars.mit.edu\u002Fdeeptraffic\">\u003Cimg src=\"images\u002Fthumb_deeptraffic.gif\">\u003C\u002Fa>\n\nDeepTraffic is a deep reinforcement learning competition. The goal is to create a neural network that drives a vehicle (or multiple vehicles) as fast as possible through dense highway traffic.\n\nLinks: \\[ [GitHub](https:\u002F\u002Fgithub.com\u002Flexfridman\u002Fdeeptraffic) \\] \\[ [Website](https:\u002F\u002Fselfdrivingcars.mit.edu\u002Fdeeptraffic) \\] \\[ [Paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F1801.02805) \\]\n\n## Team\n\n- [Lex Fridman](https:\u002F\u002Flexfridman.com)\n- [Li Ding](https:\u002F\u002Fwww.mit.edu\u002F~liding\u002F)\n- [Jack Terwilliger](https:\u002F\u002Fwww.mit.edu\u002F~jterwill\u002F)\n- [Michael Glazer](https:\u002F\u002Fwww.mit.edu\u002F~glazermi\u002F)\n- [Aleksandr Patsekin](https:\u002F\u002Fwww.mit.edu\u002F~patsekin\u002F)\n- [Aishni Parab](https:\u002F\u002Fwww.mit.edu\u002F~aishni\u002F)\n- [Dina AlAdawy](https:\u002F\u002Fwww.mit.edu\u002F~aladawy\u002F)\n- [Henri Schmidt](https:\u002F\u002Fwww.mit.edu\u002F~henris\u002F)\n","该项目是MIT深度学习相关课程的教学资源集合，包括教程、作业和竞赛。核心功能覆盖了从基础的前馈神经网络到先进的生成对抗网络（GANs）以及深度强化学习等多个方面，并提供了详细的Jupyter Notebook实例供学习者实践。技术特点上，项目充分利用了TensorFlow框架来实现模型训练与推理过程，同时支持Google Colab在线运行，方便用户无需本地配置环境即可开始学习。适合于对人工智能尤其是深度学习感兴趣的学生、研究人员及开发者使用，在自动驾驶场景分割等实际应用领域也具有很高的参考价值。","2026-06-11 03:24:03","top_topic"]