Search Results for author:
Found 45 papers, 21 papers with code
GenCast: Diffusion-based ensemble forecasting for medium-range weather
Weather forecasts are fundamentally uncertain, so predicting the range of probable weather scenarios is crucial for important decisions, from warning the public about hazardous weather, to planning renewable energy use.
Neural General Circulation Models for Weather and Climate
Here we present the first GCM that combines a differentiable solver for atmospheric dynamics with ML components, and show that it can generate forecasts of deterministic weather, ensemble weather and climate on par with the best ML and physics-based methods.
Diffusion Generative Inverse Design
Inverse design refers to the problem of optimizing the input of an objective function in order to enact a target outcome.
WeatherBench 2: A benchmark for the next generation of data-driven global weather models
WeatherBench 2 is an update to the global, medium-range (1-14 day) weather forecasting benchmark proposed by Rasp et al. (2020), designed with the aim to accelerate progress in data-driven weather modeling.
GraphCast: Learning skillful medium-range global weather forecasting
Global medium-range weather forecasting is critical to decision-making across many social and economic domains.
Learning rigid dynamics with face interaction graph networks
Simulating rigid collisions among arbitrary shapes is notoriously difficult due to complex geometry and the strong non-linearity of the interactions.
MultiScale MeshGraphNets
In recent years, there has been a growing interest in using machine learning to overcome the high cost of numerical simulation, with some learned models achieving impressive speed-ups over classical solvers whilst maintaining accuracy.
TF-GNN: Graph Neural Networks in TensorFlow
TensorFlow-GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow.
Pre-training via Denoising for Molecular Property Prediction
Many important problems involving molecular property prediction from 3D structures have limited data, posing a generalization challenge for neural networks.
Transframer: Arbitrary Frame Prediction with Generative Models
We present a general-purpose framework for image modelling and vision tasks based on probabilistic frame prediction.
Rediscovering orbital mechanics with machine learning
We then use symbolic regression to discover an analytical expression for the force law implicitly learned by the neural network, which our results showed is equivalent to Newton's law of gravitation.
Physical Design using Differentiable Learned Simulators
In our fluid manipulation tasks, the resulting designs outperformed those found by sampling-based optimization techniques.
Learned Coarse Models for Efficient Turbulence Simulation
We show that our proposed model can simulate turbulent dynamics more accurately than classical numerical solvers at the comparably low resolutions across various scientifically relevant metrics.
Constraint-based graph network simulator
We can improve the simulation accuracy on a larger system by applying more solver iterations at test time.
Learning ground states of quantum Hamiltonians with graph networks
In this work we use graph neural networks to define a structured variational manifold and optimize its parameters to find high quality approximations of the lowest energy solutions on a diverse set of Heisenberg Hamiltonians.
Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond
We introduce “Noisy Nodes”, a very simple technique for improved training of GNNs, in which we corrupt the input graph with noise, and add a noise correcting node-level loss.
Initial Structure to Relaxed Energy (IS2RE), Direct
Molecular Property Prediction
+1
Learned Simulators for Turbulence
We show that our proposed model can simulate turbulent dynamics more accurately than classical numerical solvers at the same low resolutions across various scientifically relevant metrics.
Simple GNN Regularisation for 3D Molecular Property Prediction & Beyond
From this observation we derive "Noisy Nodes", a simple technique in which we corrupt the input graph with noise, and add a noise correcting node-level loss.
Ranked #4 on
Initial Structure to Relaxed Energy (IS2RE)
on OC20
A Bayesian neural network predicts the dissolution of compact planetary systems
Our model, trained directly from short N-body time series of raw orbital elements, is more than two orders of magnitude more accurate at predicting instability times than analytical estimators, while also reducing the bias of existing machine learning algorithms by nearly a factor of three.
Graph Networks with Spectral Message Passing
Our model projects vertices of the spatial graph onto the Laplacian eigenvectors, which are each represented as vertices in a fully connected "spectral graph", and then applies learned message passing to them.
Continuous Latent Search for Combinatorial Optimization
Combinatorial optimization problems are notoriously hard because they often require enumeration of the exponentially large solution space.
Graph Neural Networks in Particle Physics
Particle physics is a branch of science aiming at discovering the fundamental laws of matter and forces.
High Energy Physics - Experiment High Energy Physics - Phenomenology
Predicting the long-term stability of compact multiplanet systems
Our Stability of Planetary Orbital Configurations Klassifier (SPOCK) predicts stability using physically motivated summary statistics measured in integrations of the first $10^4$ orbits, thus achieving speed-ups of up to $10^5$ over full simulations.
Earth and Planetary Astrophysics
Discovering Symbolic Models from Deep Learning with Inductive Biases
The technique works as follows: we first encourage sparse latent representations when we train a GNN in a supervised setting, then we apply symbolic regression to components of the learned model to extract explicit physical relations.
Lagrangian Neural Networks
Accurate models of the world are built upon notions of its underlying symmetries.
Hamiltonian Graph Networks with ODE Integrators
We introduce an approach for imposing physically informed inductive biases in learned simulation models.
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.
Learning Symbolic Physics with Graph Networks
We introduce an approach for imposing physically motivated inductive biases on graph networks to learn interpretable representations and improved zero-shot generalization.
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.
Causal Reasoning from Meta-reinforcement Learning
Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents.
CompILE: Compositional Imitation Learning and Execution
We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data.
Modeling human intuitions about liquid flow with particle-based simulation
Humans can easily describe, imagine, and, crucially, predict a wide variety of behaviors of liquids--splashing, squirting, gushing, sloshing, soaking, dripping, draining, trickling, pooling, and pouring--despite tremendous variability in their material and dynamical properties.
Learning Visual Question Answering by Bootstrapping Hard Attention
Attention mechanisms in biological perception are thought to select subsets of perceptual information for more sophisticated processing which would be prohibitive to perform on all sensory inputs.
Ranked #7 on
Visual Question Answering (VQA)
on CLEVR
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.
Graph networks as learnable physics engines for inference and control
Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model.
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.
Learning Deep Generative Models of Graphs
Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry.
Visual Interaction Networks: Learning a Physics Simulator from Video
We introduce the Visual Interaction Network, a general-purpose model for learning the dynamics of a physical system from raw visual observations.
Imagination-Augmented Agents for Deep Reinforcement Learning
We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects.
Model-based Reinforcement Learning
reinforcement-learning
+1
Learning model-based planning from scratch
Here we introduce the "Imagination-based Planner", the first model-based, sequential decision-making agent that can learn to construct, evaluate, and execute plans.
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
Visual Interaction Networks
We found that from just six input video frames the Visual Interaction Network can generate accurate future trajectories of hundreds of time steps on a wide range of physical systems.
Discovering objects and their relations from entangled scene representations
We show that RNs are capable of learning object relations from scene description data.
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.
Unsupervised Learning of 3D Structure from Images
A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world.
