Concepts:
- Gradient Descend intuition
- Convolutional Neural Networks (CNN)
- Long-Short Term Memory networks
- Generative Adversarial Networks
- Variational Autoencoders
- Approaches to Natural Language Understanding
- Neural Network Architectures in Computer Vision
Courses:
- Neural Networks in Machine Learning: Geoffrey Hinton (Coursera)
- Convolutional Neural Networks for Visual Recognition (Stanford)
- Deep Learning for Natural Language Processing (Stanford)
- Deep learning: University of Oxford (2015) by Nando de Freitas
Infrastructure, frameworks, datasets, tools:
- Infrastructure for Deep Learning (OpenAI)
- Deep Learning Frameworks Compared
- Internet: A firehose of free labelled data
Other Resources (tutorials, blogs, YouTube channels):
- Learning Reinforcement Learning (with Code, Exercises and Solutions)
- Unsupervised Feature Learning and Deep Learning Tutorial (Stanford)
- Eugenio Culurciello's blog
- Grokking Deep Learning
- DeepLearning.TV
Research papers:
- Differentiable neural computers
- Density estimation using Real NVP
- Crypto-nets: Neural networks over encrypted data
- Learning to learn by gradient descent by gradient descent
- A Clockwork RNN
Research papers in computer vision (images / videos):
- PixelCNN + PixelRNN + PixelCNN 2.0
- Image Compression with Neural Networks
- Deep Neural Networks for YouTube Recommendations
- Unsupervised Learning for Physical Interaction through Video Prediction
Research papers in reinforcement learning:
- Dynamic Frame skip Deep Q Network
- Option Discovery in Hierarchical Reinforcement Learning using Spatio-Temporal Clustering
- A2T: Attend, Adapt and Transfer: Adaptive Transfer Learning
- Learning to Poke by Poking: Experiential Learning of Intuitive Physics
- Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
Research papers in natural language processing:
- Google's Neural Machine Translation System
- SPINN: Unified Parsing and Sentence Understanding
- A Neural Knowledge Language Model (August 2016)
Research papers in audio / speech:
How you can contribute:
- Post summaries and intuitive explanations of things you read.
- Bonus points for summarizing the top research papers
- Discuss anything deep learning related
- Post links to implementations of research papers
- Post links to cool projects
- Write a review of a course you took or a lecture you watched
- Tell your friends about the community!