Stochastic Neural Networks for Quantum Devices

TL;DR

This paper introduces a method to implement and optimize stochastic neural networks on quantum circuits, enabling quantum generative AI models with various topologies and training algorithms.

Contribution

It presents a novel formulation for stochastic neural networks on quantum hardware, including training methods and diverse architectures, advancing quantum machine learning capabilities.

Findings

Successful implementation of stochastic neural networks as quantum circuits

Demonstration of quantum neural networks as oracles in Grover's algorithm

Versatile models including CNNs, autoencoders, and Hopfield networks

Abstract

This work presents a formulation to express and optimize stochastic neural networks as quantum circuits in gate-based quantum computing. Motivated by a classical perceptron, stochastic neurons are introduced and combined into a quantum neural network. The Kiefer-Wolfowitz algorithm in combination with simulated annealing is used for training the network weights. Several topologies and models are presented, including shallow fully connected networks, Hopfield Networks, Restricted Boltzmann Machines, Autoencoders and convolutional neural networks. We also demonstrate the combination of our optimized neural networks as an oracle for the Grover algorithm to realize a quantum generative AI model.