https://github.com/atcold/torch-video-tutorials

Light your way in Deep Learning with Torch 🔦
https://github.com/atcold/torch-video-tutorials

Last synced: about 1 year ago
JSON representation

Light your way in Deep Learning with Torch 🔦

• Host: GitHub
• URL: https://github.com/atcold/torch-video-tutorials
• Owner: Atcold
• Created: 2016-09-02T05:29:23.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2016-10-28T18:23:00.000Z (over 9 years ago)
• Last Synced: 2025-03-29T14:12:22.166Z (about 1 year ago)
• Language: Lua
• Homepage:
• Size: 15.9 MB
• Stars: 595
• Watchers: 50
• Forks: 98
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Torch Video Tutorials

> *Light your way in Deep Learning with* Torch :flashlight:

This aims to be a growing collections of introductory video tutorials on the [*Torch*](http://torch.ch) ecosystem.

*Torch* is one of the fastest and most flexible framework existing for Machine and Deep Learning.

And yes, flexibility was used to come with an intimidating learning curve... until now.

Enjoy the view of these videos, transcripts and quizes (you can find in the [`res`](res) folder together with some notes about how I made these videos).

## 1 - Get the basics straight

### 1.0 - An overview on *Lua* ([slides](res/1.0/slides.pdf))

[![Practical 1.0 - Lua](http://img.youtube.com/vi/QLYLOPeI92g/0.jpg)](https://youtu.be/QLYLOPeI92g?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

### 1.1 - An overview on *Torch*’s `Tensor`s ([slides](res/1.1/slides.pdf))

[![Practical 1.1 - Torch](http://img.youtube.com/vi/o3aRgD1uzsc/0.jpg)](https://youtu.be/o3aRgD1uzsc?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

### 1.2 - An overview on *Torch*’s `image` package ([slides](res/1.2/slides.pdf))

[![Practical 1.2 - image package](http://img.youtube.com/vi/dEjvydjcwOE/0.jpg)](https://youtu.be/dEjvydjcwOE?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

## 2 - Artificial Neural Networks

### 2.0 - Neural Networks – feed forward (inference) ([slides](res/2.0/slides.pdf), [quiz](res/2.0/quiz.tex))

[![Practical 2.0 – NN forward](http://img.youtube.com/vi/hxA0wxibv8g/0.jpg)](https://youtu.be/hxA0wxibv8g?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

### 2.1 - Neural Networks – back propagation (training) ([slides](res/2.1/slides.pdf), [quiz](res/2.1/quiz.tex))

[![Practical 2.1 - NN backward](http://img.youtube.com/vi/VaQUx7m3oR4/0.jpg)](https://youtu.be/VaQUx7m3oR4?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

### 2.2 - Neural Networks – An overview on *Torch*’s `nn` package ([slides](res/2.2/slides.pdf), [script](res/2.2/script.lua))

[![Practical 2.2 - nn package](http://img.youtube.com/vi/atZYdZ8hVCw/0.jpg)](https://youtu.be/atZYdZ8hVCw?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

## 3 - Convolutional Neural Networks

### 3.0 - CNN – Basics ([slides](res/3.0/slides.pdf), [`lin`](res/3.0/lin.lua), [`3conv`](res/3.0/3conv.lua), [`3conv-pool`](res/3.0/3conv-pool.lua))

[![Practical 3.0 - CNN basics](http://img.youtube.com/vi/kwCbmx3tFwY/0.jpg)](https://youtu.be/kwCbmx3tFwY?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

### 3.1 - CNN – Internals ([slides](res/3.1/slides.pdf), [script](res/3.1/script.lua), [`3conv-pool`](res/3.0/3conv-pool.lua))

[![Practical 3.1 - CNN internals](http://img.youtube.com/vi/BCensUz_gQ8/0.jpg)](https://youtu.be/BCensUz_gQ8?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

### 3.2 - CNN – Architectures ([slides](res/3.2/slides.pdf), [`LeNet5`](res/3.2/LeNet5.lua), [`AlexNet`](res/3.2/AlexNet.lua), [`GoogLeNet`](res/3.2/GoogLeNet.lua))

[![Practical 3.2 - CNN models](http://img.youtube.com/vi/LYYwUr0vCjg/0.jpg)](https://youtu.be/LYYwUr0vCjg?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

### 3.3 - CNN – Training ([slides](res/3.3/slides.pdf), [`train.lua`](res/3.3/train.lua))

[![Practical 3.3 - CNN models](http://img.youtube.com/vi/kcOJEplX7i0/0.jpg)](https://youtu.be/kcOJEplX7i0?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

### 3.4 - CNN – Loss functions ([slides](res/3.4/slides.pdf))

[![Practical 3.4 - CNN loss](http://img.youtube.com/vi/ejr6eaJKtcs/0.jpg)](https://youtu.be/ejr6eaJKtcs?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

## 4 - Recurrent Neural Networks

### 4.0 - RNN – Vectors and sequences ([slides](res/4.0/slides.pdf))

[![Practical 4.0 - RNN, vec and seq](http://img.youtube.com/vi/bUIAsEw7_9U/0.jpg)](https://youtu.be/bUIAsEw7_9U?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

### 4.1 - RNN – Forward and backward ([slides](res/4.1/slides.pdf))

[![Practical 4.1 - RNN, fwd and back](http://img.youtube.com/vi/WwslsYQX77s/0.jpg)](https://youtu.be/WwslsYQX77s?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

### 4.2 - RNN – `nngraph` package ([slides](res/4.2/slides.pdf), [script](res/4.2/script.lua))

[![Practical 4.2 - nngraph package](http://img.youtube.com/vi/FL_VTcp9jvw/0.jpg)](https://youtu.be/FL_VTcp9jvw?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

### 4.3 - RNN – Training ([slides](res/4.3/slides.pdf))

[![Practical 4.3 - RNN training](http://img.youtube.com/vi/lRN0wayLTeo/0.jpg)](https://youtu.be/lRN0wayLTeo?list=PLLHTzKZzVU9ebuL6DCclzI54MrPNFGqbW)

LSTM and training with `rnn` package coming soon! :blush: