Search Results for author: Misha Denil

Found 31 papers, 12 papers with code

$\pi2\text{vec}$: Policy Representations with Successor Features

no code implementations16 Jun 2023 Gianluca Scarpellini, Ksenia Konyushkova, Claudio Fantacci, Tom Le Paine, Yutian Chen, Misha Denil

This paper describes $\pi2\text{vec}$, a method for representing behaviors of black box policies as feature vectors.

Offline RL

Interactive decoding of words from visual speech recognition models

no code implementations1 Jul 2021 Brendan Shillingford, Yannis Assael, Misha Denil

This work describes an interactive decoding method to improve the performance of visual speech recognition systems using user input to compensate for the inherent ambiguity of the task.

speech-recognition Visual Speech Recognition

Active Offline Policy Selection

1 code implementation NeurIPS 2021 Ksenia Konyushkova, Yutian Chen, Tom Le Paine, Caglar Gulcehre, Cosmin Paduraru, Daniel J Mankowitz, Misha Denil, Nando de Freitas

We use multiple benchmarks, including real-world robotics, with a large number of candidate policies to show that the proposed approach improves upon state-of-the-art OPE estimates and pure online policy evaluation.

Bayesian Optimization Off-policy evaluation

Offline Learning from Demonstrations and Unlabeled Experience

no code implementations27 Nov 2020 Konrad Zolna, Alexander Novikov, Ksenia Konyushkova, Caglar Gulcehre, Ziyu Wang, Yusuf Aytar, Misha Denil, Nando de Freitas, Scott Reed

Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations.

Continuous Control Imitation Learning

Large-scale multilingual audio visual dubbing

no code implementations6 Nov 2020 Yi Yang, Brendan Shillingford, Yannis Assael, Miaosen Wang, Wendi Liu, Yutian Chen, Yu Zhang, Eren Sezener, Luis C. Cobo, Misha Denil, Yusuf Aytar, Nando de Freitas

The visual content is translated by synthesizing lip movements for the speaker to match the translated audio, creating a seamless audiovisual experience in the target language.


Positive-Unlabeled Reward Learning

1 code implementation1 Nov 2019 Danfei Xu, Misha Denil

Learning reward functions from data is a promising path towards achieving scalable Reinforcement Learning (RL) for robotics.

Imitation Learning Reinforcement Learning (RL)

Task-Relevant Adversarial Imitation Learning

no code implementations2 Oct 2019 Konrad Zolna, Scott Reed, Alexander Novikov, Sergio Gomez Colmenarejo, David Budden, Serkan Cabi, Misha Denil, Nando de Freitas, Ziyu Wang

We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels.

Imitation Learning

Making Efficient Use of Demonstrations to Solve Hard Exploration Problems

1 code implementation ICLR 2020 Tom Le Paine, Caglar Gulcehre, Bobak Shahriari, Misha Denil, Matt Hoffman, Hubert Soyer, Richard Tanburn, Steven Kapturowski, Neil Rabinowitz, Duncan Williams, Gabriel Barth-Maron, Ziyu Wang, Nando de Freitas, Worlds Team

This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial conditions.

Hyperbolic Attention Networks

no code implementations ICLR 2019 Caglar Gulcehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter Battaglia, Victor Bapst, David Raposo, Adam Santoro, Nando de Freitas

We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure.

Machine Translation Question Answering +2

Learning Awareness Models

no code implementations ICLR 2018 Brandon Amos, Laurent Dinh, Serkan Cabi, Thomas Rothörl, Sergio Gómez Colmenarejo, Alistair Muldal, Tom Erez, Yuval Tassa, Nando de Freitas, Misha Denil

We show that models trained to predict proprioceptive information about the agent's body come to represent objects in the external world.

Programmable Agents

no code implementations20 Jun 2017 Misha Denil, Sergio Gómez Colmenarejo, Serkan Cabi, David Saxton, Nando de Freitas

We build deep RL agents that execute declarative programs expressed in formal language.


Learned Optimizers that Scale and Generalize

1 code implementation ICML 2017 Olga Wichrowska, Niru Maheswaranathan, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Nando de Freitas, Jascha Sohl-Dickstein

Two of the primary barriers to its adoption are an inability to scale to larger problems and a limited ability to generalize to new tasks.

Learning to Perform Physics Experiments via Deep Reinforcement Learning

no code implementations6 Nov 2016 Misha Denil, Pulkit Agrawal, Tejas D. Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas

When encountering novel objects, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way.

Friction reinforcement-learning +1

Noisy Activation Functions

1 code implementation1 Mar 2016 Caglar Gulcehre, Marcin Moczulski, Misha Denil, Yoshua Bengio

Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies that are not visible to vanilla-SGD (using first order gradients only).

ACDC: A Structured Efficient Linear Layer

2 code implementations18 Nov 2015 Marcin Moczulski, Misha Denil, Jeremy Appleyard, Nando de Freitas

Finally, this paper also provides a connection between structured linear transforms used in deep learning and the field of Fourier optics, illustrating how ACDC could in principle be implemented with lenses and diffractive elements.

Deep Fried Convnets

1 code implementation ICCV 2015 Zichao Yang, Marcin Moczulski, Misha Denil, Nando de Freitas, Alex Smola, Le Song, Ziyu Wang

The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters.

Image Classification

Extraction of Salient Sentences from Labelled Documents

2 code implementations21 Dec 2014 Misha Denil, Alban Demiraj, Nando de Freitas

We present a hierarchical convolutional document model with an architecture designed to support introspection of the document structure.

Deep Multi-Instance Transfer Learning

no code implementations12 Nov 2014 Dimitrios Kotzias, Misha Denil, Phil Blunsom, Nando de Freitas

We present a new approach for transferring knowledge from groups to individuals that comprise them.

Transfer Learning

Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network

no code implementations15 Jun 2014 Misha Denil, Alban Demiraj, Nal Kalchbrenner, Phil Blunsom, Nando de Freitas

Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Processing and Information Retrieval.

Feature Engineering Information Retrieval +1

Distributed Parameter Estimation in Probabilistic Graphical Models

no code implementations NeurIPS 2014 Yariv Dror Mizrahi, Misha Denil, Nando de Freitas

This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models.

Narrowing the Gap: Random Forests In Theory and In Practice

no code implementations4 Oct 2013 Misha Denil, David Matheson, Nando de Freitas

Despite widespread interest and practical use, the theoretical properties of random forests are still not well understood.


Linear and Parallel Learning of Markov Random Fields

no code implementations29 Aug 2013 Yariv Dror Mizrahi, Misha Denil, Nando de Freitas

We introduce a new embarrassingly parallel parameter learning algorithm for Markov random fields with untied parameters which is efficient for a large class of practical models.

Predicting Parameters in Deep Learning

no code implementations NeurIPS 2013 Misha Denil, Babak Shakibi, Laurent Dinh, Marc'Aurelio Ranzato, Nando de Freitas

We demonstrate that there is significant redundancy in the parameterization of several deep learning models.

Consistency of Online Random Forests

1 code implementation20 Feb 2013 Misha Denil, David Matheson, Nando de Freitas

As a testament to their success, the theory of random forests has long been outpaced by their application in practice.

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