Stochastic Neural Networks for Quantum Devices
This work addresses the challenge of implementing neural networks on quantum devices, which could benefit researchers in quantum computing and AI, though it appears incremental as it builds on classical perceptron concepts and existing quantum algorithms.
The authors tackled the problem of expressing and optimizing stochastic neural networks as quantum circuits, achieving a formulation that includes various topologies and models such as fully connected networks and convolutional neural networks, and demonstrated its use in a quantum generative AI model via the Grover algorithm.
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.