The Physics of Learning

TL;DR

This paper explores the physical principles underlying learning machines, emphasizing thermodynamic efficiency and quantum coherence, and proposes quantum-based implementations for more energy-efficient learning.

Contribution

It connects learning processes with thermodynamic resource optimization and introduces quantum kernel evaluation as a promising energy-efficient approach.

Findings

Quantum coherence enhances data representation.

Single photon kernel evaluation demonstrates potential for low-power learning.

Physical constraints can guide the development of more efficient learning machines.

Abstract

A learning machine, like all machines, is an open system driven far from thermal equilibrium by access to a low entropy source of free energy. We discuss the connection between machines that learn, with low probability of error, and the optimal use of thermodynamic resources for both classical and quantum machines. Both fixed point and spiking perceptrons are discussed in the context of possible physical implementations. An example of a single photon quantum kernel evaluation illustrates the important role for quantum coherence in data representation. Machine learning algorithms, implemented on conventional complementary metal oxide semiconductor (CMOS) devices, currently consume large amounts of energy. By focusing on the physical constraints of learning machines rather than algorithms, we suggest that a more efficient means of implementing learning may be possible based on quantum switches operating at very low power. Single photon kernel evaluation is an example of the energy efficiency that might be possible.