R2RT · Scour

Synthetic Gradients with Tensorflow

Deconstruction with Discrete Embeddings

Beyond Binary: Ternary and One-hot Neurons

Non-Zero Initial States for Recurrent Neural Networks

Recurrent Neural Networks in Tensorflow III

Binary Stochastic Neurons in Tensorflow

Preliminary Note on the Complexity of a Neural Network

Written Memories: Understanding, Deriving and Extending the LSTM

Recurrent Neural Networks in Tensorflow II

Styles of Truncated Backpropagation

Recurrent Neural Networks in Tensorflow I

First Convergence Bias

Inverting a Neural Net

Representational Power of Deeper Layers

Implementing Batch Normalization in Tensorflow

Skill vs Strategy

Log in to enable infinite scrolling