Operationally meaningful representations of physical systems in neural networks

by   Hendrik Poulsen Nautrup, et al.

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.


page 1

page 2

page 3

page 5

page 6

page 8

page 19

page 20


Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems

Deep neural networks have become a pervasive tool in science and enginee...

Learning to Simulate Unseen Physical Systems with Graph Neural Networks

Simulation of the dynamics of physical systems is essential to the devel...

Discovering physical concepts with neural networks

The formalism of quantum physics is built upon that of classical mechani...

Redatuming physical systems using symmetric autoencoders

This paper considers physical systems described by hidden states and ind...

Quantum machine learning and quantum biomimetics: A perspective

Quantum machine learning has emerged as an exciting and promising paradi...

Learning Physical Constraints with Neural Projections

We propose a new family of neural networks to predict the behaviors of p...

Explicit Modelling of Physical Measures: From Event-B to Java

The increasing development of cyber-physical systems (CPSs) requires mod...