Search Results for author: Alex Graves

Found 34 papers, 21 papers with code

Practical Real Time Recurrent Learning with a Sparse Approximation

no code implementations ICLR 2021 Jacob Menick, Erich Elsen, Utku Evci, Simon Osindero, Karen Simonyan, Alex Graves

For highly sparse networks, SnAp with $n=2$ remains tractable and can outperform backpropagation through time in terms of learning speed when updates are done online.

A Practical Sparse Approximation for Real Time Recurrent Learning

no code implementations12 Jun 2020 Jacob Menick, Erich Elsen, Utku Evci, Simon Osindero, Karen Simonyan, Alex Graves

Current methods for training recurrent neural networks are based on backpropagation through time, which requires storing a complete history of network states, and prohibits updating the weights `online' (after every timestep).

Associative Compression Networks for Representation Learning

no code implementations6 Apr 2018 Alex Graves, Jacob Menick, Aaron van den Oord

We conclude that ACNs are a promising new direction for representation learning: one that steps away from IID modelling, and towards learning a structured description of the dataset as a whole.

Representation Learning

The Kanerva Machine: A Generative Distributed Memory

no code implementations ICLR 2018 Yan Wu, Greg Wayne, Alex Graves, Timothy Lillicrap

We present an end-to-end trained memory system that quickly adapts to new data and generates samples like them.

Noisy Networks for Exploration

14 code implementations ICLR 2018 Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Ian Osband, Alex Graves, Vlad Mnih, Remi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg

We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration.

Atari Games Efficient Exploration +1

Automated Curriculum Learning for Neural Networks

no code implementations ICML 2017 Alex Graves, Marc G. Bellemare, Jacob Menick, Remi Munos, Koray Kavukcuoglu

We introduce a method for automatically selecting the path, or syllabus, that a neural network follows through a curriculum so as to maximise learning efficiency.

Neural Machine Translation in Linear Time

10 code implementations31 Oct 2016 Nal Kalchbrenner, Lasse Espeholt, Karen Simonyan, Aaron van den Oord, Alex Graves, Koray Kavukcuoglu

The ByteNet is a one-dimensional convolutional neural network that is composed of two parts, one to encode the source sequence and the other to decode the target sequence.

Language Modelling Machine Translation +1

Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes

no code implementations NeurIPS 2016 Jack W. Rae, Jonathan J. Hunt, Tim Harley, Ivo Danihelka, Andrew Senior, Greg Wayne, Alex Graves, Timothy P. Lillicrap

SAM learns with comparable data efficiency to existing models on a range of synthetic tasks and one-shot Omniglot character recognition, and can scale to tasks requiring $100,\! 000$s of time steps and memories.

Ranked #6 on Question Answering on bAbi (Mean Error Rate metric)

Language Modelling Machine Translation +2

Video Pixel Networks

no code implementations ICML 2017 Nal Kalchbrenner, Aaron van den Oord, Karen Simonyan, Ivo Danihelka, Oriol Vinyals, Alex Graves, Koray Kavukcuoglu

The VPN approaches the best possible performance on the Moving MNIST benchmark, a leap over the previous state of the art, and the generated videos show only minor deviations from the ground truth.

 Ranked #1 on Video Prediction on KTH (Cond metric)

Video Prediction

Decoupled Neural Interfaces using Synthetic Gradients

4 code implementations ICML 2017 Max Jaderberg, Wojciech Marian Czarnecki, Simon Osindero, Oriol Vinyals, Alex Graves, David Silver, Koray Kavukcuoglu

Training directed neural networks typically requires forward-propagating data through a computation graph, followed by backpropagating error signal, to produce weight updates.

Stochastic Backpropagation through Mixture Density Distributions

no code implementations19 Jul 2016 Alex Graves

This report describes an alternative transform, applicable to any continuous multivariate distribution with a differentiable density function from which samples can be drawn, and uses it to derive an unbiased estimator for mixture density weight derivatives.

Variational Inference

Strategic Attentive Writer for Learning Macro-Actions

no code implementations NeurIPS 2016 Alexander, Vezhnevets, Volodymyr Mnih, John Agapiou, Simon Osindero, Alex Graves, Oriol Vinyals, Koray Kavukcuoglu

We present a novel deep recurrent neural network architecture that learns to build implicit plans in an end-to-end manner by purely interacting with an environment in reinforcement learning setting.

Atari Games

Memory-Efficient Backpropagation Through Time

2 code implementations NeurIPS 2016 Audrūnas Gruslys, Remi Munos, Ivo Danihelka, Marc Lanctot, Alex Graves

We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs).

Adaptive Computation Time for Recurrent Neural Networks

5 code implementations29 Mar 2016 Alex Graves

This paper introduces Adaptive Computation Time (ACT), an algorithm that allows recurrent neural networks to learn how many computational steps to take between receiving an input and emitting an output.

Language Modelling

Associative Long Short-Term Memory

3 code implementations9 Feb 2016 Ivo Danihelka, Greg Wayne, Benigno Uria, Nal Kalchbrenner, Alex Graves

We investigate a new method to augment recurrent neural networks with extra memory without increasing the number of network parameters.

Asynchronous Methods for Deep Reinforcement Learning

66 code implementations4 Feb 2016 Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, Koray Kavukcuoglu

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

Atari Games reinforcement-learning

Grid Long Short-Term Memory

1 code implementation6 Jul 2015 Nal Kalchbrenner, Ivo Danihelka, Alex Graves

This paper introduces Grid Long Short-Term Memory, a network of LSTM cells arranged in a multidimensional grid that can be applied to vectors, sequences or higher dimensional data such as images.

Language Modelling Translation

Human level control through deep reinforcement learning

2 code implementations25 Feb 2015 Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg1 & Demis Hassabis

We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters.

Atari Games reinforcement-learning

DRAW: A Recurrent Neural Network For Image Generation

20 code implementations16 Feb 2015 Karol Gregor, Ivo Danihelka, Alex Graves, Danilo Jimenez Rezende, Daan Wierstra

This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation.

Ranked #57 on Image Generation on CIFAR-10 (bits/dimension metric)

Foveation Image Generation

Neural Turing Machines

34 code implementations20 Oct 2014 Alex Graves, Greg Wayne, Ivo Danihelka

We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes.

Recurrent Models of Visual Attention

17 code implementations NeurIPS 2014 Volodymyr Mnih, Nicolas Heess, Alex Graves, Koray Kavukcuoglu

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

Hard Attention Image Classification +1

Playing Atari with Deep Reinforcement Learning

94 code implementations19 Dec 2013 Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning.

Atari Games Q-Learning +1

Generating Sequences With Recurrent Neural Networks

57 code implementations4 Aug 2013 Alex Graves

This paper shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with long-range structure, simply by predicting one data point at a time.

Language Modelling Text Generation

Sequence Transduction with Recurrent Neural Networks

6 code implementations14 Nov 2012 Alex Graves

One of the key challenges in sequence transduction is learning to represent both the input and output sequences in a way that is invariant to sequential distortions such as shrinking, stretching and translating.

Machine Translation Speech Recognition +1

Practical Variational Inference for Neural Networks

no code implementations NeurIPS 2011 Alex Graves

Variational methods have been previously explored as a tractable approximation to Bayesian inference for neural networks.

Bayesian Inference Variational Inference

Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks

no code implementations NeurIPS 2008 Alex Graves, Jürgen Schmidhuber

Offline handwriting recognition---the transcription of images of handwritten text---is an interesting task, in that it combines computer vision with sequence learning.

Handwriting Recognition

Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks

no code implementations NeurIPS 2007 Alex Graves, Marcus Liwicki, Horst Bunke, Jürgen Schmidhuber, Santiago Fernández

On-line handwriting recognition is unusual among sequence labelling tasks in that the underlying generator of the observed data, i. e. the movement of the pen, is recorded directly.

Handwriting Recognition Language Modelling

Multi-Dimensional Recurrent Neural Networks

4 code implementations14 May 2007 Alex Graves, Santiago Fernandez, Juergen Schmidhuber

Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition.

Handwriting Recognition Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.