A curated list of deep learning resource and projects inspired by @sindresorhus' awesome and @veggiemonk's awesome-docker. The primary source of the collection is from fast.ai, a spectacular deep learning course for created by Jeremy Howard and Rachel Thompson.
- Wasserstein distance Jupyter notebook
- Train a WGAN on the MNIST dataset
- Wasserstein GAN and the Kantorovich-Rubinstein Duality
- Read-through: Wasserstein GAN
- Wasserstein GAN paper
- WGAN1
- WGAN2
- LSUN data
- tips for lesson 9
- keras implementation of common models
- on aws spot instance: git clone https://github.com/jph00/part2
## application
- deep learning in regulated industry
- Equifax And SAS Leverage AI And Deep Learning To Improve Consumer Access To Credit
- curating fastai experiments
- tiling texture images
- Neural Style Transfer & Neural Doodles
- An implementation of neural style transfer
- blurify to avoid local optimization
- experiment starting point neural-style-initialization
- experiment with different optimizer
- an implementation of optimizer experiment
- Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis
- an intuitive understanding of GANs
- GANs in 50 lines
- GANs in 50 lines implementation
- Generative Adversarial Text to Image Synthesis
- DCGan
Important concepts in machine learning, deep learning and math.
-
Deep Learning Glossary - glossary of concepts related to Deep Learning
-
Gradient Descent - Gradient descent, stochastic gradient descent (SGD), and optimizing cost functions
-
Log Loss - review of log loss and cross-entropy
-
Linear Algebra for Deep Learning - review of basic Linear Algebra concepts used in Deep Learning.
-
Calculus for Deep Learning - review of basic Calculus concepts used in Deep Learning.
-
Mathematical Notation - primer/cheatsheet on math symbols
-
Linear Regression - Intro to linear regression with code examples
-
Logistic Regression - Intro to logistic regression with code examples
-
Neural Networks - Intro to neural networks and backpropagation with code examples
- storing processed image as bcolz - I don't like to store processed images as jpegs, since each processing step is going to introduce more lossy compression artifacts.
- use axel to speed up downloading - axel -n 10 www.address.com
- managing large dataset in memory and on disk
- imagenet at academic torrent