Search Results for author:
Found 58 papers, 41 papers with code
Flamingo: a Visual Language Model for Few-Shot Learning
Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research.
Ranked #1 on
Action Recognition
on RareAct
Training Compute-Optimal Large Language Models
We investigate the optimal model size and number of tokens for training a transformer language model under a given compute budget.
HiP: Hierarchical Perceiver
This however hinders them from scaling up to the inputs sizes required to process raw high-resolution images or video.
Unified Scaling Laws for Routed Language Models
The performance of a language model has been shown to be effectively modeled as a power-law in its parameter count.
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world.
Ranked #1 on
Language Modelling
on StackExchange
Improving language models by retrieving from trillions of tokens
We enhance auto-regressive language models by conditioning on document chunks retrieved from a large corpus, based on local similarity with preceding tokens.
Ranked #1 on
Language Modelling
on WikiText-103
(using extra training data)
Machine Translation Decoding beyond Beam Search
Beam search is the go-to method for decoding auto-regressive machine translation models.
Skillful Precipitation Nowcasting using Deep Generative Models of Radar
To address these challenges, we present a Deep Generative Model for the probabilistic nowcasting of precipitation from radar.
Variable-rate discrete representation learning
Semantically meaningful information content in perceptual signals is usually unevenly distributed.
High-Performance Large-Scale Image Recognition Without Normalization
Batch normalization is a key component of most image classification models, but it has many undesirable properties stemming from its dependence on the batch size and interactions between examples.
Ranked #31 on
Image Classification
on ImageNet
Practical Real Time Recurrent Learning with a Sparse Approximation
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
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).
AlgebraNets
Neural networks have historically been built layerwise from the set of functions in ${f: \mathbb{R}^n \to \mathbb{R}^m }$, i. e. with activations and weights/parameters represented by real numbers, $\mathbb{R}$.
End-to-End Adversarial Text-to-Speech
Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest.
Evolving Normalization-Activation Layers
Normalization layers and activation functions are fundamental components in deep networks and typically co-locate with each other.
Transformation-based Adversarial Video Prediction on Large-Scale Data
Recent breakthroughs in adversarial generative modeling have led to models capable of producing video samples of high quality, even on large and complex datasets of real-world video.
Ranked #9 on
Video Prediction
on Kinetics-600 12 frames, 64x64
LOGAN: Latent Optimisation for Generative Adversarial Networks
Training generative adversarial networks requires balancing of delicate adversarial dynamics.
Fast Sparse ConvNets
Equipped with our efficient implementation of sparse primitives, we show that sparse versions of MobileNet v1, MobileNet v2 and EfficientNet architectures substantially outperform strong dense baselines on the efficiency-accuracy curve.
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
When evaluated on Go, chess and shogi, without any knowledge of the game rules, MuZero matched the superhuman performance of the AlphaZero algorithm that was supplied with the game rules.
Ranked #1 on
Atari Games
on Atari 2600 Boxing
Off-Policy Actor-Critic with Shared Experience Replay
We investigate the combination of actor-critic reinforcement learning algorithms with uniform large-scale experience replay and propose solutions for two challenges: (a) efficient actor-critic learning with experience replay (b) stability of off-policy learning where agents learn from other agents behaviour.
Ranked #6 on
Atari Games
on Atari-57
High Fidelity Speech Synthesis with Adversarial Networks
However, their application in the audio domain has received limited attention, and autoregressive models, such as WaveNet, remain the state of the art in generative modelling of audio signals such as human speech.
Adversarial Video Generation on Complex Datasets
Generative models of natural images have progressed towards high fidelity samples by the strong leveraging of scale.
Ranked #1 on
Video Generation
on Kinetics-600 12 frames, 128x128
3D Character Animation From A Single Photo
Video Generation
+1
Large Scale Adversarial Representation Learning
We extensively evaluate the representation learning and generation capabilities of these BigBiGAN models, demonstrating that these generation-based models achieve the state of the art in unsupervised representation learning on ImageNet, as well as in unconditional image generation.
Ranked #10 on
Contrastive Learning
on imagenet-1k
Non-Differentiable Supervised Learning with Evolution Strategies and Hybrid Methods
While using ES for differentiable parameters is computationally impractical (although possible), we show that a hybrid approach is practically feasible in the case where the model has both differentiable and non-differentiable parameters.
Hierarchical Autoregressive Image Models with Auxiliary Decoders
We show that autoregressive models conditioned on these representations can produce high-fidelity reconstructions of images, and that we can train autoregressive priors on these representations that produce samples with large-scale coherence.
The StreetLearn Environment and Dataset
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.
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal.
Ranked #1 on
Image Generation
on CIFAR-10
(NFE metric)
Conditional Image Generation
Vocal Bursts Intensity Prediction
This Time with Feeling: Learning Expressive Musical Performance
Music generation has generally been focused on either creating scores or interpreting them.
The challenge of realistic music generation: modelling raw audio at scale
It has been shown that autoregressive models excel at generating raw audio waveforms of speech, but when applied to music, we find them biased towards capturing local signal structure at the expense of modelling long-range correlations.
DARTS: Differentiable Architecture Search
This paper addresses the scalability challenge of architecture search by formulating the task in a differentiable manner.
Learning to Navigate in Cities Without a Map
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.
Kickstarting Deep Reinforcement Learning
Our method places no constraints on the architecture of the teacher or student agents, and it regulates itself to allow the students to surpass their teachers in performance.
Efficient Neural Audio Synthesis
The small number of weights in a Sparse WaveRNN makes it possible to sample high-fidelity audio on a mobile CPU in real time.
Learning to Search with MCTSnets
They are most typically solved by tree search algorithms that simulate ahead into the future, evaluate future states, and back-up those evaluations to the root of a search tree.
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters.
Ranked #3 on
Atari Games
on Atari 2600 Skiing
(using extra training data)
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
The game of chess is the most widely-studied domain in the history of artificial intelligence.
Ranked #1 on
Game of Go
on ELO Ratings
Parallel WaveNet: Fast High-Fidelity Speech Synthesis
The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system.
Population Based Training of Neural Networks
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.
Hierarchical Representations for Efficient Architecture Search
We explore efficient neural architecture search methods and show that a simple yet powerful evolutionary algorithm can discover new architectures with excellent performance.
StarCraft II: A New Challenge for Reinforcement Learning
Finally, we present initial baseline results for canonical deep reinforcement learning agents applied to the StarCraft II domain.
Ranked #1 on
Starcraft II
on MoveToBeacon
The Kinetics Human Action Video Dataset
We describe the DeepMind Kinetics human action video dataset.
Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders
Generative models in vision have seen rapid progress due to algorithmic improvements and the availability of high-quality image datasets.
Neural Machine Translation in Linear Time
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.
Ranked #1 on
Machine Translation
on WMT2015 English-German
Video Pixel Networks
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)
WaveNet: A Generative Model for Raw Audio
This paper introduces WaveNet, a deep neural network for generating raw audio waveforms.
Ranked #1 on
Speech Synthesis
on Mandarin Chinese
Natural Neural Networks
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.
Spatial Transformer Networks
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.
Deep Structured Output Learning for Unconstrained Text Recognition
We develop a representation suitable for the unconstrained recognition of words in natural images: the general case of no fixed lexicon and unknown length.
Reading Text in the Wild with Convolutional Neural Networks
In this work we present an end-to-end system for text spotting -- localising and recognising text in natural scene images -- and text based image retrieval.
Ranked #15 on
Scene Text Detection
on ICDAR 2013
Very Deep Convolutional Networks for Large-Scale Image Recognition
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting.
Ranked #2 on
Classification
on InDL
Efficient On-the-fly Category Retrieval using ConvNets and GPUs
We investigate the gains in precision and speed, that can be obtained by using Convolutional Networks (ConvNets) for on-the-fly retrieval - where classifiers are learnt at run time for a textual query from downloaded images, and used to rank large image or video datasets.
Two-Stream Convolutional Networks for Action Recognition in Videos
Our architecture is trained and evaluated on the standard video actions benchmarks of UCF-101 and HMDB-51, where it is competitive with the state of the art.
Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
In this work we present a framework for the recognition of natural scene text.
Ranked #37 on
Scene Text Recognition
on SVT
A Compact and Discriminative Face Track Descriptor
Our goal is to learn a compact, discriminative vector representation of a face track, suitable for the face recognition tasks of verification and classification.
Understanding Objects in Detail with Fine-Grained Attributes
We show that the collected data can be used to study the relation between part detection and attribute prediction by diagnosing the performance of classifiers that pool information from different parts of an object.
Return of the Devil in the Details: Delving Deep into Convolutional Nets
In particular, we show that the data augmentation techniques commonly applied to CNN-based methods can also be applied to shallow methods, and result in an analogous performance boost.
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets).
Deep Fisher Networks for Large-Scale Image Classification
As massively parallel computations have become broadly available with modern GPUs, deep architectures trained on very large datasets have risen in popularity.
