Search Results for author:
Found 30 papers, 16 papers with code
Low Bias Low Variance Gradient Estimates for Hierarchical Boolean Stochastic Networks
Stochastic neural networks with discrete random variables are an important class of models for their expressiveness and interpretability.
CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay
Our method iterates between 1) program sampling and hindsight relabeling, and 2) learning from prioritized experience replay.
A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems
In these graphs, the geometric attributes transform according to the inherent physical symmetries of 3D atomic systems, including rotations and translations in Euclidean space, as well as node permutations.
FoMo Rewards: Can we cast foundation models as reward functions?
We explore the viability of casting foundation models as generic reward functions for reinforcement learning.
Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers
The Geometric Algebra Transformer (GATr) is a versatile architecture for geometric deep learning based on projective geometric algebra.
BISCUIT: Causal Representation Learning from Binary Interactions
Identifying the causal variables of an environment and how to intervene on them is of core value in applications such as robotics and embodied AI.
Geometric Algebra Transformer
In this paper we introduce the Geometric Algebra Transformer (GATr), a general-purpose architecture for geometric data.
On the Expressive Power of Geometric Graph Neural Networks
The expressive power of Graph Neural Networks (GNNs) has been studied extensively through the Weisfeiler-Leman (WL) graph isomorphism test.
Deconfounded Imitation Learning
Standard imitation learning can fail when the expert demonstrators have different sensory inputs than the imitating agent.
A PAC-Bayesian Generalization Bound for Equivariant Networks
Equivariant networks capture the inductive bias about the symmetry of the learning task by building those symmetries into the model.
Towards a Grounded Theory of Causation for Embodied AI
There exist well-developed frameworks for causal modelling, but these require rather a lot of human domain expertise to define causal variables and perform interventions.
Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems
To address this issue, we propose iCITRIS, a causal representation learning method that allows for instantaneous effects in intervened temporal sequences when intervention targets can be observed, e. g., as actions of an agent.
Equivariant Mesh Attention Networks
Equivariance to symmetries has proven to be a powerful inductive bias in deep learning research.
Weakly supervised causal representation learning
Learning high-level causal representations together with a causal model from unstructured low-level data such as pixels is impossible from observational data alone.
CITRIS: Causal Identifiability from Temporal Intervened Sequences
Understanding the latent causal factors of a dynamical system from visual observations is considered a crucial step towards agents reasoning in complex environments.
Transformer-based Transform Coding
Neural data compression based on nonlinear transform coding has made great progress over the last few years, mainly due to improvements in prior models, quantization methods and nonlinear transforms.
Efficient Neural Causal Discovery without Acyclicity Constraints
Learning the structure of a causal graphical model using both observational and interventional data is a fundamental problem in many scientific fields.
Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
The last decade has witnessed an experimental revolution in data science and machine learning, epitomised by deep learning methods.
Parallelized Rate-Distortion Optimized Quantization Using Deep Learning
We train two classes of neural networks, a fully-convolutional network and an auto-regressive network, and evaluate each as a post-quantization step designed to refine cheap quantization schemes such as scalar quantization (SQ).
Natural Graph Networks
A key requirement for graph neural networks is that they must process a graph in a way that does not depend on how the graph is described.
Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs
A common approach to define convolutions on meshes is to interpret them as a graph and apply graph convolutional networks (GCNs).
Gauge Equivariant Spherical CNNs
Spherical CNNs are convolutional neural networks that can process signals on the sphere, such as global climate and weather patterns or omnidirectional images.
Low Bias Gradient Estimates for Very Deep Boolean Stochastic Networks
In this work we focus on stochastic networks with multiple layers of Boolean latent variables.
A General Theory of Equivariant CNNs on Homogeneous Spaces
Feature maps in these networks represent fields on a homogeneous base space, and layers are equivariant maps between spaces of fields.
3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
We prove that equivariant convolutions are the most general equivariant linear maps between fields over R^3.
Rotation Equivariant CNNs for Digital Pathology
We propose a new model for digital pathology segmentation, based on the observation that histopathology images are inherently symmetric under rotation and reflection.
Ranked #7 on
Breast Tumour Classification
on PCam
Convolutional Networks for Spherical Signals
Many areas of science and egineering deal with signals with other symmetries, such as rotation invariant data on the sphere.
Teacher-Student Curriculum Learning
We propose Teacher-Student Curriculum Learning (TSCL), a framework for automatic curriculum learning, where the Student tries to learn a complex task and the Teacher automatically chooses subtasks from a given set for the Student to train on.
Learning the Irreducible Representations of Commutative Lie Groups
We present a new probabilistic model of compact commutative Lie groups that produces invariant-equivariant and disentangled representations of data.
