https://github.com/daviddao/deep-learning-notes

deep learning for the visually impaired
https://github.com/daviddao/deep-learning-notes

Last synced: about 1 month ago
JSON representation

deep learning for the visually impaired

• Host: GitHub
• URL: https://github.com/daviddao/deep-learning-notes
• Owner: daviddao
• Created: 2015-02-22T16:07:54.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2015-03-06T07:58:59.000Z (over 9 years ago)
• Last Synced: 2024-05-01T20:25:39.906Z (7 months ago)
• Homepage:
• Size: 152 KB
• Stars: 1
• Watchers: 4
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# kaggle-challenge

Deep Learning for Diabetic Retinopathy Detection

### Resources

This is a list of resources on deep learning

#### Programming Tools

##### [cuDNN](https://developer.nvidia.com/cuDNN)

NVIDIA cuDNN is a GPU-accelerated library of primitives for deep neural networks. It emphasizes performance, ease-of-use, and low memory overhead. NVIDIA cuDNN is designed to be integrated into higher-level machine learning frameworks, such as UC Berkeley’s popular Caffe software. 

##### [Caffe](http://caffe.berkeleyvision.org/)

Caffe is a C/C++ deep learning framework made with expression, speed, and modularity in mind.

##### [Cuda-convnet2](https://code.google.com/p/cuda-convnet2/)

This is a fast C++/CUDA implementation of convolutional (or more generally, feed-forward) neural networks. It can model arbitrary layer connectivity and network depth. Any directed acyclic graph of layers will do. Training is done using the back-propagation algorithm.

##### [Theano](http://deeplearning.net/software/theano/)

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. You can find here a [tutorial](https://github.com/Newmu/Theano-Tutorials).

##### [Torch](http://torch.ch/) 

Torch is a scientific computing framework with wide support for machine learning algorithms. It is easy to use and efficient, thanks to an easy and fast scripting language, LuaJIT, and an underlying C/CUDA implementation.

#### Awesome Implementations

##### [convnetjs](http://cs.stanford.edu/people/karpathy/convnetjs/index.html) 

Awesome convnet implementation in js

##### [recurrentjs](http://cs.stanford.edu/people/karpathy/recurrentjs/)

Recurrent net implementation in js

##### [neuraltalk](https://github.com/karpathy/neuraltalk)

NLP on images in python

##### 

#### Education/Scripts

Really useful resources to learn about deep learning ranked after personal importance

##### [CS231n Stanford](http://cs231n.github.io/)

Awesome Stanford Course and Script about ConvNets

##### [CS244d Stanford](http://cs224d.stanford.edu/)

Awesome Stanford Course and Script about RecurrentNets

##### [Colahs Blog](http://colah.github.io/)

Understandable mathematical insights about neural nets

##### [Metacademy](http://www.metacademy.org/roadmaps/rgrosse/deep_learning)

Deep Learning Guide

##### [Deep Learning Textbook](http://www.iro.umontreal.ca/~bengioy/dlbook/)

Textbook on Deep Learning

##### [Nvidia Deep Learning](https://developer.nvidia.com/deep-learning)

Resource collection

##### [deeplearning.net](http://deeplearning.net/)

Website all about deep learning

#### Stuff

##### [Talking Machines Podcast](http://www.thetalkingmachines.com/)