Quantum activation functions for quantum neural networks

TL;DR

This paper introduces a quantum algorithm capable of approximating any analytic activation function for quantum neural networks, enabling universal approximation without measurement collapse, thus advancing quantum machine learning architectures.

Contribution

It provides a general method to realize arbitrary activation functions on quantum computers, filling a key gap in quantum neural network design.

Findings

Allows approximation of any analytic activation function to arbitrary accuracy

Enables quantum neural networks to have universal approximation capabilities

Operates without the need for irreversible measurements

Abstract

The field of artificial neural networks is expected to strongly benefit from recent developments of quantum computers. In particular, quantum machine learning, a class of quantum algorithms which exploit qubits for creating trainable neural networks, will provide more power to solve problems such as pattern recognition, clustering and machine learning in general. The building block of feed-forward neural networks consists of one layer of neurons connected to an output neuron that is activated according to an arbitrary activation function. The corresponding learning algorithm goes under the name of Rosenblatt perceptron. Quantum perceptrons with specific activation functions are known, but a general method to realize arbitrary activation functions on a quantum computer is still lacking. Here we fill this gap with a quantum algorithm which is capable to approximate any analytic activation functions to any given order of its power series. Unlike previous proposals providing irreversible measurement--based and simplified activation functions, here we show how to approximate any analytic function to any required accuracy without the need to measure the states encoding the information. Thanks to the generality of this construction, any feed-forward neural network may acquire the universal approximation properties according to Hornik's theorem. Our results recast the science of artificial neural networks in the architecture of gate-model quantum computers.