Light your way in Deep Learning with Torch πŸ”¦
Lua TeX Shell
Latest commit 7136d7c Oct 28, 2016 @Atcold Add Practicals 4.3
Permalink
Failed to load latest commit information.
res Add Practicals 4.3 Oct 28, 2016
README.md Add Practicals 4.3 Oct 28, 2016

README.md

Torch Video Tutorials

Light your way in Deep Learning with Torch πŸ”¦

This aims to be a growing collections of introductory video tutorials on the Torch 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 folder together with some notes about how I made these videos).

1 - Get the basics straight

1.0 - An overview on Lua (slides)

Practical 1.0 - Lua

1.1 - An overview on Torch’s Tensors (slides)

Practical 1.1 - Torch

1.2 - An overview on Torch’s image package (slides)

Practical 1.2 - image package

2 - Artificial Neural Networks

2.0 - Neural Networks – feed forward (inference) (slides, quiz)

Practical 2.0 – NN forward

2.1 - Neural Networks – back propagation (training) (slides, quiz)

Practical 2.1 - NN backward

2.2 - Neural Networks – An overview on Torch’s nn package (slides, script)

Practical 2.2 - nn package

3 - Convolutional Neural Networks

3.0 - CNN – Basics (slides, lin, 3conv, 3conv-pool)

Practical 3.0 - CNN basics

3.1 - CNN – Internals (slides, script, 3conv-pool)

Practical 3.1 - CNN internals

3.2 - CNN – Architectures (slides, LeNet5, AlexNet, GoogLeNet)

Practical 3.2 - CNN models

3.3 - CNN – Training (slides, train.lua)

Practical 3.3 - CNN models

3.4 - CNN – Loss functions (slides)

Practical 3.4 - CNN loss

4 - Recurrent Neural Networks

4.0 - RNN – Vectors and sequences (slides)

Practical 4.0 - RNN, vec and seq

4.1 - RNN – Forward and backward (slides)

Practical 4.1 - RNN, fwd and back

4.2 - RNN – nngraph package (slides, script)

Practical 4.2 - nngraph package

4.3 - RNN – Training (slides)

Practical 4.3 - RNN training

LSTM and training with rnn package coming soon! 😊