Search Results for author: Koray Kavukcuoglu

Found 51 papers, 38 papers with code

Scaling Language Models: Methods, Analysis & Insights from Training Gopher

no code implementations NA 2021 Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican, Jordan Hoffmann, Francis Song, John Aslanides, Sarah Henderson, Roman Ring, Susannah Young, Eliza Rutherford, Tom Hennigan, Jacob Menick, Albin Cassirer, Richard Powell, George van den Driessche, Lisa Anne Hendricks, Maribeth Rauh, Po-Sen Huang, Amelia Glaese, Johannes Welbl, Sumanth Dathathri, Saffron Huang, Jonathan Uesato, John Mellor, Irina Higgins, Antonia Creswell, Nat McAleese, Amy Wu, Erich Elsen, Siddhant Jayakumar, Elena Buchatskaya, David Budden, Esme Sutherland, Karen Simonyan, Michela Paganini, Laurent SIfre, Lena Martens, Xiang Lorraine Li, Adhiguna Kuncoro, Aida Nematzadeh, Elena Gribovskaya, Domenic Donato, Angeliki Lazaridou, Arthur Mensch, Jean-Baptiste Lespiau, Maria Tsimpoukelli, Nikolai Grigorev, Doug Fritz, Thibault Sottiaux, Mantas Pajarskas, Toby Pohlen, Zhitao Gong, Daniel Toyama, Cyprien de Masson d'Autume, Yujia Li, Tayfun Terzi, Vladimir Mikulik, Igor Babuschkin, Aidan Clark, Diego de Las Casas, Aurelia Guy, Chris Jones, James Bradbury, Matthew Johnson, Blake Hechtman, Laura Weidinger, Iason Gabriel, William Isaac, Ed Lockhart, Simon Osindero, Laura Rimell, Chris Dyer, Oriol Vinyals, Kareem Ayoub, Jeff Stanway, Lorrayne Bennett, Demis Hassabis, Koray Kavukcuoglu, Geoffrey Irving

Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world.

Fact Checking Language Modelling +3

The StreetLearn Environment and Dataset

1 code implementation4 Mar 2019 Piotr Mirowski, Andras Banki-Horvath, Keith Anderson, Denis Teplyashin, Karl Moritz Hermann, Mateusz Malinowski, Matthew Koichi Grimes, Karen Simonyan, Koray Kavukcuoglu, Andrew Zisserman, Raia Hadsell

These datasets cannot be used for decision-making and reinforcement learning, however, and in general the perspective of navigation as an interactive learning task, where the actions and behaviours of a learning agent are learned simultaneously with the perception and planning, is relatively unsupported.

Decision Making

Learning to Navigate in Cities Without a Map

3 code implementations NeurIPS 2018 Piotr Mirowski, Matthew Koichi Grimes, Mateusz Malinowski, Karl Moritz Hermann, Keith Anderson, Denis Teplyashin, Karen Simonyan, Koray Kavukcuoglu, Andrew Zisserman, Raia Hadsell

We present an interactive navigation environment that uses Google StreetView for its photographic content and worldwide coverage, and demonstrate that our learning method allows agents to learn to navigate multiple cities and to traverse to target destinations that may be kilometres away.

Autonomous Navigation reinforcement-learning

Population Based Training of Neural Networks

6 code implementations27 Nov 2017 Max Jaderberg, Valentin Dalibard, Simon Osindero, Wojciech M. Czarnecki, Jeff Donahue, Ali Razavi, Oriol Vinyals, Tim Green, Iain Dunning, Karen Simonyan, Chrisantha Fernando, Koray Kavukcuoglu

Neural networks dominate the modern machine learning landscape, but their training and success still suffer from sensitivity to empirical choices of hyperparameters such as model architecture, loss function, and optimisation algorithm.

Machine Translation Model Selection

Neural Discrete Representation Learning

40 code implementations NeurIPS 2017 Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu

Learning useful representations without supervision remains a key challenge in machine learning.

Representation Learning

Hierarchical Representations for Efficient Architecture Search

1 code implementation ICLR 2018 Hanxiao Liu, Karen Simonyan, Oriol Vinyals, Chrisantha Fernando, Koray Kavukcuoglu

We explore efficient neural architecture search methods and show that a simple yet powerful evolutionary algorithm can discover new architectures with excellent performance.

General Classification Image Classification +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.

Understanding Synthetic Gradients and Decoupled Neural Interfaces

1 code implementation ICML 2017 Wojciech Marian Czarnecki, Grzegorz Świrszcz, Max Jaderberg, Simon Osindero, Oriol Vinyals, Koray Kavukcuoglu

When training neural networks, the use of Synthetic Gradients (SG) allows layers or modules to be trained without update locking - without waiting for a true error gradient to be backpropagated - resulting in Decoupled Neural Interfaces (DNIs).

Interaction Networks for Learning about Objects, Relations and Physics

6 code implementations NeurIPS 2016 Peter W. Battaglia, Razvan Pascanu, Matthew Lai, Danilo Rezende, Koray Kavukcuoglu

Here we introduce the interaction network, a model which can reason about how objects in complex systems interact, supporting dynamical predictions, as well as inferences about the abstract properties of the system.

Reinforcement Learning with Unsupervised Auxiliary Tasks

3 code implementations16 Nov 2016 Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki, Tom Schaul, Joel Z. Leibo, David Silver, Koray Kavukcuoglu

We also introduce a novel mechanism for focusing this representation upon extrinsic rewards, so that learning can rapidly adapt to the most relevant aspects of the actual task.


Combining policy gradient and Q-learning

no code implementations5 Nov 2016 Brendan O'Donoghue, Remi Munos, Koray Kavukcuoglu, Volodymyr Mnih

Policy gradient is an efficient technique for improving a policy in a reinforcement learning setting.

Atari Games Q-Learning

Sample Efficient Actor-Critic with Experience Replay

8 code implementations3 Nov 2016 Ziyu Wang, Victor Bapst, Nicolas Heess, Volodymyr Mnih, Remi Munos, Koray Kavukcuoglu, Nando de Freitas

This paper presents an actor-critic deep reinforcement learning agent with experience replay that is stable, sample efficient, and performs remarkably well on challenging environments, including the discrete 57-game Atari domain and several continuous control problems.

Continuous Control reinforcement-learning

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

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.

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

Progressive Neural Networks

9 code implementations15 Jun 2016 Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, Raia Hadsell

Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding catastrophic forgetting--remains a key obstacle to achieving human-level intelligence.

Continual Learning reinforcement-learning

Exploiting Cyclic Symmetry in Convolutional Neural Networks

no code implementations8 Feb 2016 Sander Dieleman, Jeffrey De Fauw, Koray Kavukcuoglu

We evaluate the effect of these architectural modifications on three datasets which exhibit rotational symmetry and demonstrate improved performance with smaller models.

Data Augmentation Translation

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

Pixel Recurrent Neural Networks

16 code implementations25 Jan 2016 Aaron van den Oord, Nal Kalchbrenner, Koray Kavukcuoglu

Modeling the distribution of natural images is a landmark problem in unsupervised learning.

Image Generation

Policy Distillation

1 code implementation19 Nov 2015 Andrei A. Rusu, Sergio Gomez Colmenarejo, Caglar Gulcehre, Guillaume Desjardins, James Kirkpatrick, Razvan Pascanu, Volodymyr Mnih, Koray Kavukcuoglu, Raia Hadsell

Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve good performance.


Natural Neural Networks

1 code implementation NeurIPS 2015 Guillaume Desjardins, Karen Simonyan, Razvan Pascanu, Koray Kavukcuoglu

We introduce Natural Neural Networks, a novel family of algorithms that speed up convergence by adapting their internal representation during training to improve conditioning of the Fisher matrix.

online learning

Spatial Transformer Networks

44 code implementations NeurIPS 2015 Max Jaderberg, Karen Simonyan, Andrew Zisserman, Koray Kavukcuoglu

Convolutional Neural Networks define an exceptionally powerful class of models, but are still limited by the lack of ability to be spatially invariant to the input data in a computationally and parameter efficient manner.


Weight Uncertainty in Neural Networks

32 code implementations20 May 2015 Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, Daan Wierstra

We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop.

Bayesian Inference General Classification +1

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

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

Unsupervised Feature Learning by Deep Sparse Coding

no code implementations20 Dec 2013 Yunlong He, Koray Kavukcuoglu, Yun Wang, Arthur Szlam, Yanjun Qi

In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (DeepSC), that extends sparse coding to a multi-layer architecture for visual object recognition tasks.

Object Recognition

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

Learning word embeddings efficiently with noise-contrastive estimation

no code implementations NeurIPS 2013 Andriy Mnih, Koray Kavukcuoglu

Continuous-valued word embeddings learned by neural language models have recently been shown to capture semantic and syntactic information about words very well, setting performance records on several word similarity tasks.

Learning Word Embeddings Word Similarity

Learning the Dependency Structure of Latent Factors

no code implementations NeurIPS 2012 Yunlong He, Yanjun Qi, Koray Kavukcuoglu, Haesun Park

In this paper, we study latent factor models with the dependency structure in the latent space.

Natural Language Processing (almost) from Scratch

1 code implementation2 Mar 2011 Ronan Collobert, Jason Weston, Leon Bottou, Michael Karlen, Koray Kavukcuoglu, Pavel Kuksa

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunking, named entity recognition, and semantic role labeling.

Chunking Named Entity Recognition +2

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