Classical Artificial Neural Network Training Using Quantum Walks as a Search Procedure

This article proposes a computational procedure that applies a quantum algorithm to train classical artificial neural networks. The goal of the procedure is to apply quantum walk as a search algorithm in a complete graph to find all synaptic weights of a classical artificial neural network. Each vertex of this complete graph represents a possible synaptic weight set in the w-dimensional search space, where w is the number of weights of the neural network. To know the number of iterations required a priorito obtain the solutions is one of the main advantages of the procedure. Another advantage is that the proposed method does not stagnate in local minimums. Thus, it is possible to use the quantum walk search procedure as an alternative to the backpropagation algorithm. The proposed method was employed fora XOR problem to prove the proposed concept. To solve this problem, the proposed method trained a classical artificial neural network with nine weights. However, the procedure can find solutions for any number of dimensions. The results achieved demonstrate the viability of the proposal, contributing to machine learning and quantum computing researches.

Automated summary

This article proposes a computational procedure that applies a quantum algorithm to train classical artificial neural networks. By using quantum walk as a search algorithm in a complete graph, the procedure can find all synaptic weights of the neural network. With the advantages of knowing the required number of iterations in advance and avoiding getting stuck in local minimums, this method offers an alternative to the backpropagation algorithm.