YouTube Video
Master modern neural networks by recreating the groundbreaking discoveries of Geoffrey Hinton, the visionary whose research redefined computer science and deep learning. Covering his defining papers, this course directly bridges historical breakthroughs to readable PyTorch code. This hands on coding course will give you a unified look at how today's AI landscape was engineered through one pioneer’s vision.
This course follows the evolution of deep learning, from Boltzmann Machines and Backpropagation to Deep Belief Networks, Dropout, Knowledge Distillation, Capsule Networks, the Forward-Forward Algorithm, and t-SNE.
Course developed by @programmingoceanacademy
https://github.com/MOHAMMEDFAHD/Geoffrey-Hinton-Papers-Replicating-In-Pytorch
❤️ Support for this channel comes from our friends at Scrimba – the coding platform that's reinvented interactive learning: https://scrimba.com/freecodecamp
Chapters
- 0:00:00 welcoming
- 0:01:31 Introduction
- 0:02:39 Objectives
- 0:04:23 Acknowledgement
- 0:05:10 Disclaimer
- 0:06:03 GitHub repo tour
- 0:08:25 A Learning Algorithm for Boltzmann Machine
- 1:29:06 Learning representations by back-propagating errors
- 3:32:10 Distributed Representations
- 4:40:46 Adaptive Mixtures of Local Experts
- 6:01:47 The Helmholtz Machine
- 7:17:07 The Wake-Sleep Algorithm for Unsupervised Neural Networks
- 8:33:43 Stochastic Neighbour Embeddings
- 9:32:12 A Fast Learning Algorithm For Deep Belief Networks
- 10:50:09 Reducing The Dimensionality Of Data With Neural Networks
- 12:21:06 Visualizing Data Using T-SNE
- 13:52:30 Deep Boltzmann Machine
- 14:49:35 Rectified Linear Units Improve Restricted Boltzmann Machine
- 16:44:09 ImageNet Classification With Deep Convolutional Neural Networks
- 17:54:12 Dropout: A Simple Way to Prevent Neural Network From Overfitting
- 18:41:42 Distilling the Knowledge in a Neural Network
- 20:02:54 Layer Normalization
- 22:43:52 Dynamic Routing Between Capsules
- 24:36:55 A Simple Framework for Contrastive Learning of Visual Representations
- 25:53:31 The Forward-Forward Algorithm: Some Preliminary Investigations
- 27:27:17 The Ending
🎉 Thanks to our Champion and Sponsor supporters:
👾 @omerhattapoglu1158
👾 @goddardtan
👾 @akihayashi6629
👾 @kikilogsin
👾 @anthonycampbell2148
👾 @tobymiller7790
👾 @rajibdassharma497
👾 @CloudVirtualizationEnthusiast
👾 @adilsoncarlosvianacarlos
👾 @martinmacchia1564
👾 @ulisesmoralez4160
👾 @_Oscar_
👾 @jedi-or-sith2728
👾 @justinhual1290
--
Learn to code for free and get a developer job: https://www.freecodecamp.org
Read hundreds of articles on programming: https://freecodecamp.org/news
This course follows the evolution of deep learning, from Boltzmann Machines and Backpropagation to Deep Belief Networks, Dropout, Knowledge Distillation, Capsule Networks, the Forward-Forward Algorithm, and t-SNE.
Course developed by @programmingoceanacademy
https://github.com/MOHAMMEDFAHD/Geoffrey-Hinton-Papers-Replicating-In-Pytorch
❤️ Support for this channel comes from our friends at Scrimba – the coding platform that's reinvented interactive learning: https://scrimba.com/freecodecamp
Chapters
- 0:00:00 welcoming
- 0:01:31 Introduction
- 0:02:39 Objectives
- 0:04:23 Acknowledgement
- 0:05:10 Disclaimer
- 0:06:03 GitHub repo tour
- 0:08:25 A Learning Algorithm for Boltzmann Machine
- 1:29:06 Learning representations by back-propagating errors
- 3:32:10 Distributed Representations
- 4:40:46 Adaptive Mixtures of Local Experts
- 6:01:47 The Helmholtz Machine
- 7:17:07 The Wake-Sleep Algorithm for Unsupervised Neural Networks
- 8:33:43 Stochastic Neighbour Embeddings
- 9:32:12 A Fast Learning Algorithm For Deep Belief Networks
- 10:50:09 Reducing The Dimensionality Of Data With Neural Networks
- 12:21:06 Visualizing Data Using T-SNE
- 13:52:30 Deep Boltzmann Machine
- 14:49:35 Rectified Linear Units Improve Restricted Boltzmann Machine
- 16:44:09 ImageNet Classification With Deep Convolutional Neural Networks
- 17:54:12 Dropout: A Simple Way to Prevent Neural Network From Overfitting
- 18:41:42 Distilling the Knowledge in a Neural Network
- 20:02:54 Layer Normalization
- 22:43:52 Dynamic Routing Between Capsules
- 24:36:55 A Simple Framework for Contrastive Learning of Visual Representations
- 25:53:31 The Forward-Forward Algorithm: Some Preliminary Investigations
- 27:27:17 The Ending
🎉 Thanks to our Champion and Sponsor supporters:
👾 @omerhattapoglu1158
👾 @goddardtan
👾 @akihayashi6629
👾 @kikilogsin
👾 @anthonycampbell2148
👾 @tobymiller7790
👾 @rajibdassharma497
👾 @CloudVirtualizationEnthusiast
👾 @adilsoncarlosvianacarlos
👾 @martinmacchia1564
👾 @ulisesmoralez4160
👾 @_Oscar_
👾 @jedi-or-sith2728
👾 @justinhual1290
--
Learn to code for free and get a developer job: https://www.freecodecamp.org
Read hundreds of articles on programming: https://freecodecamp.org/news
SOCIAL SHARE CARD GENERATOR