This section provides an overview of what deep-learning is, and why a developer might want to use it.
It should also mention any large subjects within deep-learning, and link out to the related topics. Since the Documentation for deep-learning is new, you may need to create initial versions of those related topics.
Installation or Setup
Detailed instructions on getting deep-learning framework set up or installed.
Most frameworks supports interfaces in several languages:
- Caffe (C++, Python, Matlab)
- Tensorflow (C++, Python)
- Theano, Theano wrappers (Keras, Lasagne) (Python)
- Torch (Lua)
- Matconvnet (Matlab)
Every framework includes a getting started and an example of how to run a model on the MNIST dataset. It is recommended to first tryout the MNIST example as it provides a sense of the framework.
stackoverflow documentation already includes getting started page for the following frameworks:
Resources to learn deep Learning:
Deep Learning Book (Link): Written by some of the most accomplished deep learning researcher. It is an excellent resource to first learn about deep learning and also to learn about new and fascinating topics in deep learning.
Deep Learning Tutorial (Link): A more in depth explanation of deep learning and its reliance on machine learning for theano. However all of the concepts explained here are applicable for the other frameworks.
Neural Network CLass (Link): This is a more in depth course on neural networks. This is a more advanced resource to learn more about neural networks, CRFs, Boltzmann Machines and deep learning.