Search Results for author:
Found 16 papers, 9 papers with code
Relational inductive biases, deep learning, and graph networks
As a companion to this paper, we have released an open-source software library for building graph networks, with demonstrations of how to use them in practice.
Synthetic Returns for Long-Term Credit Assignment
We propose state-associative (SA) learning, where the agent learns associations between states and arbitrarily distant future rewards, then propagates credit directly between the two.
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
Our method enforces a total compute budget by capping the number of tokens ($k$) that can participate in the self-attention and MLP computations at a given layer.
A simple neural network module for relational reasoning
Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn.
Image Retrieval with Multi-Modal Query
Question Answering
+2
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.
Relational recurrent neural networks
Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods.
Ranked #72 on
Language Modelling
on WikiText-103
An investigation of model-free planning
The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity.
Causal Reasoning from Meta-reinforcement Learning
Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents.
Symbolic Behaviour in Artificial Intelligence
This approach will allow for AI to interpret something as symbolic on its own rather than simply manipulate things that are only symbols to human onlookers, and thus will ultimately lead to AI with more human-like symbolic fluency.
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.
Discovering objects and their relations from entangled scene representations
We show that RNs are capable of learning object relations from scene description data.
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.
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.
Rapid Task-Solving in Novel Environments
We show that EPNs learn to execute a value iteration-like planning algorithm and that they generalize to situations beyond their training experience.
AlignNet: Self-supervised Alignment Module
The natural world consists of objects that we perceive as persistent in space and time, even though these objects appear, disappear and reappear in our field of view as we move.
A data-driven approach for learning to control computers
It would be useful for machines to use computers as humans do so that they can aid us in everyday tasks.
