
A Practical Sparse Approximation for Real Time Recurrent Learning
Current methods for training recurrent neural networks are based on back...
read it

Associative Compression Networks for Representation Learning
This paper introduces Associative Compression Networks (ACNs), a new fra...
read it

Associative Compression Networks
This paper introduces Associative Compression Networks (ACNs), a new fra...
read it

The Kanerva Machine: A Generative Distributed Memory
We present an endtoend trained memory system that quickly adapts to ne...
read it

Parallel WaveNet: Fast HighFidelity Speech Synthesis
The recentlydeveloped WaveNet architecture is the current state of the ...
read it

Noisy Networks for Exploration
We introduce NoisyNet, a deep reinforcement learning agent with parametr...
read it

Automated Curriculum Learning for Neural Networks
We introduce a method for automatically selecting the path, or syllabus,...
read it

Neural Machine Translation in Linear Time
We present a novel neural network for processing sequences. The ByteNet ...
read it

Scaling MemoryAugmented Neural Networks with Sparse Reads and Writes
Neural networks augmented with external memory have the ability to learn...
read it

Video Pixel Networks
We propose a probabilistic video model, the Video Pixel Network (VPN), t...
read it

WaveNet: A Generative Model for Raw Audio
This paper introduces WaveNet, a deep neural network for generating raw ...
read it

Decoupled Neural Interfaces using Synthetic Gradients
Training directed neural networks typically requires forwardpropagating...
read it

Stochastic Backpropagation through Mixture Density Distributions
The ability to backpropagate stochastic gradients through continuous lat...
read it

Conditional Image Generation with PixelCNN Decoders
This work explores conditional image generation with a new image density...
read it

Strategic Attentive Writer for Learning MacroActions
We present a novel deep recurrent neural network architecture that learn...
read it

MemoryEfficient Backpropagation Through Time
We propose a novel approach to reduce memory consumption of the backprop...
read it

Adaptive Computation Time for Recurrent Neural Networks
This paper introduces Adaptive Computation Time (ACT), an algorithm that...
read it

Associative Long ShortTerm Memory
We investigate a new method to augment recurrent neural networks with ex...
read it

Asynchronous Methods for Deep Reinforcement Learning
We propose a conceptually simple and lightweight framework for deep rein...
read it

Grid Long ShortTerm Memory
This paper introduces Grid Long ShortTerm Memory, a network of LSTM cel...
read it

DRAW: A Recurrent Neural Network For Image Generation
This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural ...
read it

Neural Turing Machines
We extend the capabilities of neural networks by coupling them to extern...
read it

Recurrent Models of Visual Attention
Applying convolutional neural networks to large images is computationall...
read it

Playing Atari with Deep Reinforcement Learning
We present the first deep learning model to successfully learn control p...
read it

Generating Sequences With Recurrent Neural Networks
This paper shows how Long Shortterm Memory recurrent neural networks ca...
read it

Speech Recognition with Deep Recurrent Neural Networks
Recurrent neural networks (RNNs) are a powerful model for sequential dat...
read it

Sequence Transduction with Recurrent Neural Networks
Many machine learning tasks can be expressed as the transformationor ...
read it

Phoneme recognition in TIMIT with BLSTMCTC
We compare the performance of a recurrent neural network with the best r...
read it

MultiDimensional Recurrent Neural Networks
Recurrent neural networks (RNNs) have proved effective at one dimensiona...
read it
Alex Graves
is this you? claim profile
Alex Graves is a DeepMind research scientist. He received a BSc in Theoretical Physics from Edinburgh and an AI PhD from IDSIA under Jürgen Schmidhuber. He was also a postdoctoral graduate at TU Munich and at the University of Toronto under Geoffrey Hinton.
At IDSIA, he trained longterm neural memory networks by a new method called connectionist time classification. In certain applications, this method outperformed traditional voice recognition models. In 2009, his CTCtrained LSTM was the first repeat neural network to win pattern recognition contests, winning a number of handwriting awards.
This is a very popular method. Google uses CTCtrained LSTM for smartphone voice recognition.Graves also designs the neural Turing machines and the related neural computer.