路线图 | 深度学习从入门到放弃

1. Overview

• Organization
  • 

　　Machine Learning 　　----> 　　Deep Learning

　　　　　　　　　　　　　　　　　　　　　　　　 　　　　---->　　Deep Reinforcement Learning [Learning Road Map]

　　　　　　　　　　　　　　　　  Reinforcement Learning

• Architecture

  • Post: Neural Network Architectures (updating continuously)

2. Paper Set

• Deep Learning Papers Reading Roadmap

3. Courses

• UVA DEEP LEARNING COURSE

• Udacity: Deep Learning

• Data Science: Deep Learning in Python

• Bay Area Deep Learning School

• 7—EXOTIC CNN ARCHITECTURES; RNN FROM SCRATCH

4. Applications

• Computer Vision

  • Imgage Clissification

  • Action Recognition

• Natural Language Processing

5. Set up

• Post: Deep Learning Workbench Installation Notes

6. Tutorials & Practices

• 5 Genius Python Deep Learning Libraries:

  • Theano is a low-level library that specializes in efficient computation. You'll only use this directly if you need fine-grain customization and flexibility.

  • TensorFlow is another low-level library that is less mature than Theano. However, it's supported by Google and offers out-of-the-box distributed computing.

  • Lasagne is a lightweight wrapper for Theano. Use this if need the flexibility of Theano but don't want to always write neural network layers from scratch.

  • Keras is a heavyweight wrapper for both Theano and Tensorflow. It's minimalistic, modular, and awesome for rapid experimentation. This is our favorite Python library for deep learning and the best place to start for beginners.

  • MXNet is another high-level library similar to Keras. It offers bindings for multiple languages and support for distributed computing.

• Post: Getting started with Tensorflow