Search Results for author:
Found 35 papers, 14 papers with code
How will advanced AI systems impact democracy?
Advanced AI systems capable of generating humanlike text and multimodal content are now widely available.
DiscoGen: Learning to Discover Gene Regulatory Networks
To accurately identify GRNs, perturbational data is required.
Meta-Learned Models of Cognition
Meta-learning is a framework for learning learning algorithms through repeated interactions with an environment as opposed to designing them by hand.
Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution
Neuroscience has long been an essential driver of progress in artificial intelligence (AI).
HCMD-zero: Learning Value Aligned Mechanisms from Data
Our analysis shows HCMD-zero consistently makes the mechanism policy more and more likely to be preferred by human participants over the course of training, and that it results in a mechanism with an interpretable and intuitive policy.
General-purpose, long-context autoregressive modeling with Perceiver AR
Real-world data is high-dimensional: a book, image, or musical performance can easily contain hundreds of thousands of elements even after compression.
Ranked #35 on
Language Modelling
on WikiText-103
Human-centered mechanism design with Democratic AI
Building artificial intelligence (AI) that aligns with human values is an unsolved problem.
SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition
Leveraging the shared structure that exists across different scenes, our model learns to infer two sets of latent representations from RGB video input alone: a set of "object" latents, corresponding to the time-invariant, object-level contents of the scene, as well as a set of "frame" latents, corresponding to global time-varying elements such as viewpoint.
Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents
There has been rapidly growing interest in meta-learning as a method for increasing the flexibility and sample efficiency of reinforcement learning.
Neural spatio-temporal reasoning with object-centric self-supervised learning
Transformer-based language models have proved capable of rudimentary symbolic reasoning, underlining the effectiveness of applying self-attention computations to sets of discrete entities.
Deep Reinforcement Learning and its Neuroscientific Implications
The emergence of powerful artificial intelligence is defining new research directions in neuroscience.
The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget
This is typically the case when we have a standard conditioning input, such as a state observation, and a "privileged" input, which might correspond to the goal of a task, the output of a costly planning algorithm, or communication with another agent.
MEMO: A Deep Network for Flexible Combination of Episodic Memories
First, it introduces a separation between memories (facts) stored in external memory and the items that comprise these facts in external memory.
Environmental drivers of systematicity and generalization in a situated agent
The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI.
Meta-learning of Sequential Strategies
In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class.
Deep reinforcement learning with relational inductive biases
We introduce an approach for augmenting model-free deep reinforcement learning agents with a mechanism for relational reasoning over structured representations, which improves performance, learning efficiency, generalization, and interpretability.
Transfer and Exploration via the Information Bottleneck
In new environments, this model can then identify novel subgoals for further exploration, guiding the agent through a sequence of potential decision states and through new regions of the state space.
Is coding a relevant metaphor for building AI? A commentary on "Is coding a relevant metaphor for the brain?", by Romain Brette
Brette contends that the neural coding metaphor is an invalid basis for theories of what the brain does.
Multi-Object Representation Learning with Iterative Variational Inference
Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities.
InfoBot: Transfer and Exploration via the Information Bottleneck
In new environments, this model can then identify novel subgoals for further exploration, guiding the agent through a sequence of potential decision states and through new regions of the state space.
Causal Reasoning from Meta-reinforcement Learning
Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents.
Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning
We present the Bayesian action decoder (BAD), a new multi-agent learning method that uses an approximate Bayesian update to obtain a public belief that conditions on the actions taken by all agents in the environment.
Relational Forward Models for Multi-Agent Learning
The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to operate in them.
Relational Deep Reinforcement Learning
We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perception and relational reasoning.
Been There, Done That: Meta-Learning with Episodic Recall
Meta-learning agents excel at rapidly learning new tasks from open-ended task distributions; yet, they forget what they learn about each task as soon as the next begins.
On the importance of single directions for generalization
Finally, we find that class selectivity is a poor predictor of task importance, suggesting not only that networks which generalize well minimize their dependence on individual units by reducing their selectivity, but also that individually selective units may not be necessary for strong network performance.
Machine Theory of Mind
We design a Theory of Mind neural network -- a ToMnet -- which uses meta-learning to build models of the agents it encounters, from observations of their behaviour alone.
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
Domain adaptation is an important open problem in deep reinforcement learning (RL).
SCAN: Learning Hierarchical Compositional Visual Concepts
SCAN learns concepts through fast symbol association, grounding them in disentangled visual primitives that are discovered in an unsupervised manner.
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
Learning an interpretable factorised representation of the independent data generative factors of the world without supervision is an important precursor for the development of artificial intelligence that is able to learn and reason in the same way that humans do.
One-shot Learning with Memory-Augmented Neural Networks
Despite recent breakthroughs in the applications of deep neural networks, one setting that presents a persistent challenge is that of "one-shot learning."
Design Principles of the Hippocampal Cognitive Map
Furthermore, we demonstrate that this representation of space can support efficient reinforcement learning.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
A systematic approach to extracting semantic information from functional MRI data
This paper introduces a novel classification method for functional magnetic resonance imaging datasets with tens of classes.
Goal-directed decision making in prefrontal cortex: a computational framework
Research in animal learning and behavioral neuroscience has distinguished between two forms of action control: a habit-based form, which relies on stored action values, and a goal-directed form, which forecasts and compares action outcomes based on a model of the environment.
