Alex Graves

Human-level control through deep reinforcement learning

Asynchronous Methods for Deep Reinforcement Learning

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network contro...

Speech recognition with deep recurrent neural networks

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RN...

Connectionist temporal classification

Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal ...

Framewise phoneme classification with bidirectional LSTM and other neural network architectures

Supervised Sequence Labelling with Recurrent Neural Networks

Practical Variational Inference for Neural Networks

Variational methods have been previously explored as a tractable approximation to Bayesian inference for neural networks. However the approaches proposed so far have only been a...

Offline Arabic Handwriting Recognition with Multidimensional Recurrent Neural Networks

Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks

In online handwriting recognition the trajectory of the pen is recorded during writing. Although the trajectory provides a compact and complete representation of the written out...

Sequence Transduction with Recurrent Neural Networks

Many machine learning tasks can be expressed as the transformation---or \emph{transduction}---of input sequences into output sequences: speech recognition, machine translation, ...

DRAW: A Recurrent Neural Network For Image Generation

This paper introduces the Deep Recurrent Atten-tive Writer (DRAW) neural network architecture for image generation. DRAW networks combine a novel spatial attention mechanism tha...

Recurrent Models of Visual Attention

Applying convolutional neural networks to large images is computationally ex-pensive because the amount of computation scales linearly with the number of image pixels. We presen...

Recurrent Models of Visual Attention

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present...