“第十七章 深度学习”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
（→‎高级读者）
 
（相同用户的15个中间修订版本未显示）
第1行： 第1行：
  
 +
==教学资料==
 +
*[[教学参考-17|教学参考]]
 +
*[http://aigraph.cslt.org/courses/17/course-17.pptx 课件]
 +
*小清爱提问：什么是深度学习（上）？[https://mp.weixin.qq.com/s?__biz=Mzk0NjIzMzI2MQ==&mid=2247487252&idx=1&sn=b3dac3e2afbe2b7ebff901ba358ee3e0&chksm=c30805d6f47f8cc02d8a284fb416c7767f815861f3656a605378bbf6caf718f11191637b81de&scene=178#rd]
 +
*小清爱提问：什么是深度学习（下）？[https://mp.weixin.qq.com/s?__biz=Mzk0NjIzMzI2MQ==&mid=2247487260&idx=1&sn=c6ee1b8e09fcec9d9dfc96ddd06d874f&chksm=c30805def47f8cc8498b5c77c0ad720b45f02e78126fe9ed06e0a4465d3a970874b229692f29&scene=178#rd]
  
−
* ConvNetJS 深度神经网络演示 [https://cs.stanford.edu/people/karpathy/convnetjs/]
+
==扩展阅读==
  
−
* ConvNetJS 代码 [https://github.com/karpathy/convnetjs]
+
*AI100问：什么是深度学习？[http://aigraph.cslt.org/ai100/AI-100-48-什么是深度学习.pdf]
 +
*维基百科：深度学习 [http://aigraph.cslt.org/courses/17/深度学习.pdf][http://aigraph.cslt.org/courses/17/Deep_learning.pdf]
 +
*维基百科：杰弗里·辛顿 [http://aigraph.cslt.org/courses/17/杰弗里·辛顿.pdf][http://aigraph.cslt.org/courses/17/Geoffrey_Hinton.pdf]
 +
*维基百科：约书亚·本希奥 [http://aigraph.cslt.org/courses/17/约书亚·本希奥.pdf][http://aigraph.cslt.org/courses/17/Yoshua_Bengio.pdf]
 +
*维基百科：杨立昆 [http://aigraph.cslt.org/courses/17/杨立昆.pdf][http://aigraph.cslt.org/courses/17/Yann_LeCun.pdf]
 +
*维基百科：通用近似定理[http://aigraph.cslt.org/courses/17/Universal_approximation_theorem.pdf][http://aigraph.cslt.org/courses/17/通用近似定理.pdf]
  
−
* Leiden  Demo for image classification [http://destiny.liacs.nl/]
+
==视频展示==
  
−
* CNN explainer[https://poloclub.github.io/cnn-explainer/]
+
*VGG Net visualization [http://aigraph.cslt.org/courses/17/VGG16.mp4]
 +
*Disclaimer CNN 展示 [http://aigraph.cslt.org/courses/16/CNN_visulization.mp4]
  
−
* 可解释机器学习 [https://poloclub.github.io/]
+
==演示链接==
−
 
+
−
===Demo===
+
  
 +
* ConvNetJS 深度神经网络演示 [https://cs.stanford.edu/people/karpathy/convnetjs/]
 +
* Leiden  Demo for image classification [http://destiny.liacs.nl/]
 +
* CNN explainer[https://poloclub.github.io/cnn-explainer/]
 
* Quick style transfer [https://tenso.rs/demos/fast-neural-style/]
 
* Quick style transfer [https://tenso.rs/demos/fast-neural-style/]
 
* Pix2Pix[https://affinelayer.com/pixsrv/]
 
* Pix2Pix[https://affinelayer.com/pixsrv/]
 
* AutoWriter[https://cyborg.tenso.rs/]
 
* AutoWriter[https://cyborg.tenso.rs/]
 +
* HoggingFace 演示[https://www.kdnuggets.com/2022/05/top-10-machine-learning-demos-hugging-face-spaces-edition.html]
 +
* CNN visualization [https://distill.pub/2017/feature-visualization/]
 +
 +
==开发者资源==
 +
 +
*Georgia Tech, Polo Club (可解释机器学习) [https://poloclub.github.io/]
 +
*Google developer courses [*][https://developers.google.com/machine-learning/crash-course?hl=zh-cn]
 +
*ConvNetJS 代码 [https://github.com/karpathy/convnetjs]
  
−
===开发者资源===
+
==高级读者==
  
−
*Google developer courses [https://developers.google.com/machine-learning/crash-course?hl=zh-cn]
+
* LeCun Y, Bengio Y, Hinton G. Deep learning[J]. nature, 2015, 521(7553): 436-444.[https://s3.us-east-2.amazonaws.com/hkg-website-assets/static/pages/files/DeepLearning.pdf]
 +
* Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25. [https://proceedings.neurips.cc/paper/2012/file/c399862d3b9d6b76c8436e924a68c45b-Paper.pdf]
 +
* Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. science, 2006, 313(5786): 504-507. [https://asset-pdf.scinapse.io/prod/2100495367/2100495367.pdf]
 +
* Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural computation, 2006, 18(7): 1527-1554. [https://www.cs.utoronto.ca/~hinton/absps/ncfast.pdf]
 +
* Universal approximation theorem [*][https://medium.com/analytics-vidhya/neural-networks-and-the-universal-approximation-theorem-e5c387982eed]
 +
* 王东，机器学习导论,第三章，神经模型，2021,清华大学出版社 [http://mlbook.cslt.org]
 +
* Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning [https://www.deeplearningbook.org/]

2023年8月13日 (日) 01:43的最后版本

教学资料

  • 教学参考
  • 课件
  • 小清爱提问：什么是深度学习（上）？[1]
  • 小清爱提问：什么是深度学习（下）？[2]

扩展阅读

  • AI100问：什么是深度学习？[3]
  • 维基百科：深度学习 [4][5]
  • 维基百科：杰弗里·辛顿 [6][7]
  • 维基百科：约书亚·本希奥 [8][9]
  • 维基百科：杨立昆 [10][11]
  • 维基百科：通用近似定理[12][13]

视频展示

  • VGG Net visualization [14]
  • Disclaimer CNN 展示 [15]

演示链接

  • ConvNetJS 深度神经网络演示 [16]
  • Leiden Demo for image classification [17]
  • CNN explainer[18]
  • Quick style transfer [19]
  • Pix2Pix[20]
  • AutoWriter[21]
  • HoggingFace 演示[22]
  • CNN visualization [23]

开发者资源

  • Georgia Tech, Polo Club (可解释机器学习) [24]
  • Google developer courses [*][25]
  • ConvNetJS 代码 [26]

高级读者

  • LeCun Y, Bengio Y, Hinton G. Deep learning[J]. nature, 2015, 521(7553): 436-444.[27]
  • Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[J]. Advances in neural information processing systems, 2012, 25. [28]
  • Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. science, 2006, 313(5786): 504-507. [29]
  • Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural computation, 2006, 18(7): 1527-1554. [30]
  • Universal approximation theorem [*][31]
  • 王东，机器学习导论,第三章，神经模型，2021,清华大学出版社 [32]
  • Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep Learning [33]
取自“http://index.cslt.org/mediawiki/index.php?title=第十七章_深度学习&oldid=40543”