Search Results for author:
Found 31 papers, 12 papers with code
Consistency of Online Random Forests
As a testament to their success, the theory of random forests has long been outpaced by their application in practice.
Predicting Parameters in Deep Learning
We demonstrate that there is significant redundancy in the parameterization of several deep learning models.
Linear and Parallel Learning of Markov Random Fields
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.
Narrowing the Gap: Random Forests In Theory and In Practice
Despite widespread interest and practical use, the theoretical properties of random forests are still not well understood.
Distributed Parameter Estimation in Probabilistic Graphical Models
This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models.
Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network
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.
Deep Multi-Instance Transfer Learning
We present a new approach for transferring knowledge from groups to individuals that comprise them.
Extraction of Salient Sentences from Labelled Documents
We present a hierarchical convolutional document model with an architecture designed to support introspection of the document structure.
Deep Fried Convnets
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.
Ranked #54 on
Image Classification
on MNIST
ACDC: A Structured Efficient Linear Layer
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.
Noisy Activation Functions
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).
Learning to learn by gradient descent by gradient descent
The move from hand-designed features to learned features in machine learning has been wildly successful.
Learning to Perform Physics Experiments via Deep Reinforcement Learning
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.
Learning to Learn without Gradient Descent by Gradient Descent
We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent.
Learning to Navigate in Complex Environments
Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents.
Learned Optimizers that Scale and Generalize
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.
Programmable Agents
We build deep RL agents that execute declarative programs expressed in formal language.
The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously
This paper introduces the Intentional Unintentional (IU) agent.
Learning Awareness Models
We show that models trained to predict proprioceptive information about the agent's body come to represent objects in the external world.
Hyperbolic Attention Networks
We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure.
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
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.
Scaling data-driven robotics with reward sketching and batch reinforcement learning
We present a framework for data-driven robotics that makes use of a large dataset of recorded robot experience and scales to several tasks using learned reward functions.
Task-Relevant Adversarial Imitation Learning
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.
Positive-Unlabeled Reward Learning
Learning reward functions from data is a promising path towards achieving scalable Reinforcement Learning (RL) for robotics.
Large-scale multilingual audio visual dubbing
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.
Offline Learning from Demonstrations and Unlabeled Experience
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.
Active Offline Policy Selection
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.
Interactive decoding of words from visual speech recognition models
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.
Vision-Language Models as Success Detectors
Detecting successful behaviour is crucial for training intelligent agents.
$\pi2\text{vec}$: Policy Representations with Successor Features
This paper describes $\pi2\text{vec}$, a method for representing behaviors of black box policies as feature vectors.
RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation
With RoboCat, we demonstrate the ability to generalise to new tasks and robots, both zero-shot as well as through adaptation using only 100-1000 examples for the target task.
