Tunable Quantum Neural Networks in the QPAC-Learning Framework

TL;DR

This paper explores tunable quantum neural networks within the QPAC-learning framework, demonstrating their ability to approximate Boolean functions and efficiently learn simple concepts using an amplitude amplification-based tuning algorithm.

Contribution

It introduces a novel quantum neural network architecture with tunable controls and an amplitude amplification algorithm for concept learning in the QPAC framework.

Findings

Networks can approximate any Boolean function.

The tuning algorithm effectively learns simple concepts.

Numerical results validate the approach's efficiency.

Abstract

In this paper, we investigate the performances of tunable quantum neural networks in the Quantum Probably Approximately Correct (QPAC) learning framework. Tunable neural networks are quantum circuits made of multi-controlled X gates. By tuning the set of controls these circuits are able to approximate any Boolean functions. This architecture is particularly suited to be used in the QPAC-learning framework as it can handle the superposition produced by the oracle. In order to tune the network so that it can approximate a target concept, we have devised and implemented an algorithm based on amplitude amplification. The numerical results show that this approach can efficiently learn concepts from a simple class.