The Hintons in your Neural Network: a Quantum Field Theory View of Deep Learning

TL;DR

This paper introduces a quantum field theory framework for deep learning, representing neural network components as quantum entities, which offers new insights, potential for quantum computing implementation, and semi-classical approximations for classical simulation.

Contribution

It develops a novel quantum field theory formalism for neural networks, representing layers as quantum gates and excitations as particles, enabling quantum computing applications and classical approximations.

Findings

Quantum formalism models neural layers as quantum gates.

Introduction of 'Hintons' as fundamental excitations.

Quantum deformations enable efficient quantum computing implementations.

Abstract

In this work we develop a quantum field theory formalism for deep learning, where input signals are encoded in Gaussian states, a generalization of Gaussian processes which encode the agent's uncertainty about the input signal. We show how to represent linear and non-linear layers as unitary quantum gates, and interpret the fundamental excitations of the quantum model as particles, dubbed ``Hintons''. On top of opening a new perspective and techniques for studying neural networks, the quantum formulation is well suited for optical quantum computing, and provides quantum deformations of neural networks that can be run efficiently on those devices. Finally, we discuss a semi-classical limit of the quantum deformed models which is amenable to classical simulation.