Inverse design refers to the problem of optimizing the input of an objective function in order to enact a target outcome.
1 code implementation • 29 Aug 2023 • Stephan Rasp, Stephan Hoyer, Alexander Merose, Ian Langmore, Peter Battaglia, Tyler Russel, Alvaro Sanchez-Gonzalez, Vivian Yang, Rob Carver, Shreya Agrawal, Matthew Chantry, Zied Ben Bouallegue, Peter Dueben, Carla Bromberg, Jared Sisk, Luke Barrington, Aaron Bell, Fei Sha
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.
1 code implementation • 24 Dec 2022 • Remi Lam, Alvaro Sanchez-Gonzalez, Matthew Willson, Peter Wirnsberger, Meire Fortunato, Ferran Alet, Suman Ravuri, Timo Ewalds, Zach Eaton-Rosen, Weihua Hu, Alexander Merose, Stephan Hoyer, George Holland, Oriol Vinyals, Jacklynn Stott, Alexander Pritzel, Shakir Mohamed, Peter Battaglia
Global medium-range weather forecasting is critical to decision-making across many social and economic domains.
Simulating rigid collisions among arbitrary shapes is notoriously difficult due to complex geometry and the strong non-linearity of the interactions.
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.
1 code implementation • 7 Jul 2022 • Oleksandr Ferludin, Arno Eigenwillig, Martin Blais, Dustin Zelle, Jan Pfeifer, Alvaro Sanchez-Gonzalez, Wai Lok Sibon Li, Sami Abu-El-Haija, Peter Battaglia, Neslihan Bulut, Jonathan Halcrow, Filipe Miguel Gonçalves de Almeida, Pedro Gonnet, Liangze Jiang, Parth Kothari, Silvio Lattanzi, André Linhares, Brandon Mayer, Vahab Mirrokni, John Palowitch, Mihir Paradkar, Jennifer She, Anton Tsitsulin, Kevin Villela, Lisa Wang, David Wong, Bryan Perozzi
TensorFlow-GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow.
Many important problems involving molecular property prediction from 3D structures have limited data, posing a generalization challenge for neural networks.
We present a general-purpose framework for image modelling and vision tasks based on probabilistic frame prediction.
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.
In our fluid manipulation tasks, the resulting designs outperformed those found by sampling-based optimization techniques.
no code implementations • 31 Dec 2021 • Kimberly Stachenfeld, Drummond B. Fielding, Dmitrii Kochkov, Miles Cranmer, Tobias Pfaff, Jonathan Godwin, Can Cui, Shirley Ho, Peter Battaglia, Alvaro Sanchez-Gonzalez
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.
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.
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.
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.
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
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.
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.
Combinatorial optimization problems are notoriously hard because they often require enumeration of the exponentially large solution space.
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
1 code implementation • 13 Jul 2020 • Daniel Tamayo, Miles Cranmer, Samuel Hadden, Hanno Rein, Peter Battaglia, Alysa Obertas, Philip J. Armitage, Shirley Ho, David Spergel, Christian Gilbertson, Naireen Hussain, Ari Silburt, Daniel Jontof-Hutter, Kristen Menou
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
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.
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.
We introduce an approach for imposing physically motivated inductive biases on graph networks to learn interpretable representations and improved zero-shot generalization.
no code implementations • • Vinicius Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David Reichert, Timothy Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew Botvinick, Oriol Vinyals, Peter Battaglia
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.
Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents.
We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data.
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.
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
7 code implementations • 5 Jun 2018 • Vinicius Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David Reichert, Timothy Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew Botvinick, Oriol Vinyals, Peter Battaglia
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.
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.
no code implementations • • Caglar Gulcehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter Battaglia, Victor Bapst, David Raposo, Adam Santoro, Nando de Freitas
We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure.
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.
We introduce the Visual Interaction Network, a general-purpose model for learning the dynamics of a physical system from raw visual observations.
2 code implementations • • Théophane Weber, Sébastien Racanière, David P. Reichert, Lars Buesing, Arthur Guez, Danilo Jimenez Rezende, Adria Puigdomènech Badia, Oriol Vinyals, Nicolas Heess, Yujia Li, Razvan Pascanu, Peter Battaglia, Demis Hassabis, David Silver, Daan Wierstra
We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects.
Here we introduce the "Imagination-based Planner", the first model-based, sequential decision-making agent that can learn to construct, evaluate, and execute plans.
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.
Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn.
We show that RNs are capable of learning object relations from scene description data.
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.