Operationally meaningful representations of physical systems in neural networks

Abstract

To make progress in science, we often build abstract representations of physical systems that meaningfully encode information about the systems. The representations learnt by most current machine learning techniques reflect statistical structure present in the training data; however, these methods do not allow us to specify explicit and operationally meaningful requirements on the representation. Here, we present a neural network architecture based on the notion that agents dealing with different aspects of a physical system should be able to communicate relevant information as efficiently as possible to one another. This produces representations that separate different parameters which are useful for making statements about the physical system in different experimental settings. We present examples involving both classical and quantum physics. For instance, our architecture finds a compact representation of an arbitrary two-qubit system that separates local parameters from parameters describing quantum correlations. We further show that this method can be combined with reinforcement learning to enable representation learning within interactive scenarios where agents need to explore experimental settings to identify relevant variables.

arXiv comment24 pages, 13 figures

References in corpus (48)

• Auto-Encoding Variational Bayes
• Neural Machine Translation by Jointly Learning to Align and Translate
• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Explainable Machine Learning for Scientific Insights and Discoveries
• Disentangling by Factorising
• Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation
• Twisted Photons: New Quantum Perspectives in High Dimensions
• Discovering physical concepts with neural networks
• Reconstructing quantum states with generative models
• State Representation Learning for Control: An Overview
• Active learning machine learns to create new quantum experiments
• Reinforcement Learning with Unsupervised Auxiliary Tasks
• Neural Relational Inference for Interacting Systems
• Automated Search for new Quantum Experiments
• Reinforcement Learning with Neural Networks for Quantum Feedback
• Neural-Network Quantum States, String-Bond States, and Chiral Topological States
• Learning New Physics from a Machine
• Optimizing Quantum Error Correction Codes with Reinforcement Learning
• Entanglement by Path Identity
• Machine learning out-of-equilibrium phases of matter
• Guiding New Physics Searches with Unsupervised Learning
• Machine learning for long-distance quantum communication
• Entangled Bloch Spheres: Bloch Matrix and Two Qubit State Space
• The Consciousness Prior
• Toward an AI Physicist for Unsupervised Learning
• Quantum Experiments and Graphs: Multiparty States as coherent superpositions of Perfect Matchings
• Neural network quantum state tomography in a two-qubit experiment
• Quantum circuit optimization with deep reinforcement learning
• Visualizing operators of coupled spin systems
• Attention-based Quantum Tomography
• Graying the black box: Understanding DQNs
• Probabilistic Simulation of Quantum Circuits with the Transformer
• Unsupervised Learning of Latent Physical Properties Using Perception-Prediction Networks
• Disentangling the independently controllable factors of variation by interacting with the world
• Projective simulation with generalization
• Independently Controllable Features
• Modelling collective motion based on the principle of agency
• Photonic architecture for reinforcement learning
• Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU
• Benchmarking projective simulation in navigation problems
• Emergent Quantum Mechanics in an Introspective Machine Learning Architecture
• On the convergence of projective-simulation-based reinforcement learning in Markov decision processes
• Skill Learning by Autonomous Robotic Playing using Active Learning and Creativity
• How a minimal learning agent can infer the existence of unobserved variables in a complex environment
• Learning Generalizable Physical Dynamics of 3D Rigid Objects
• Learning the Arrow of Time
• Adding Intuitive Physics to Neural-Symbolic Capsules Using Interaction Networks

Cited by in corpus (14)

• Experimental quantum speed-up in reinforcement learning agents
• Computer-inspired Quantum Experiments
• Learning models of quantum systems from experiments
• Learning minimal representations of stochastic processes with variational autoencoders
• Hybrid discrete-continuous compilation of trapped-ion quantum circuits with deep reinforcement learning
• Deep learning insights into cosmological structure formation
• Explainable Representation Learning of Small Quantum States
• $\beta$-Variational Autoencoder as an Entanglement Classifier
• Observing Schrödinger's Cat with Artificial Intelligence: Emergent Classicality from Information Bottleneck
• Learning the dynamics of Markovian open quantum systems from experimental data
• Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering
• Forming complex neurons by four-wave mixing in a Bose-Einstein condensate
• Interpretable representation learning of quantum data enabled by probabilistic variational autoencoders
• Learning Physical Concepts in Cyber-Physical Systems: A Case Study