Exact Learning with Tunable Quantum Neural Networks and a Quantum Example Oracle

TL;DR

This paper introduces a tunable quantum neural network architecture within the quantum exact learning framework, utilizing amplitude amplification to efficiently learn positive k-juntas with a quantum example oracle, and provides bounds on the number of examples needed.

Contribution

It presents a novel approach combining tunable quantum neural networks with amplitude amplification for exact learning, and analyzes bounds for learning positive k-juntas.

Findings

O(n^2 2^k) quantum examples suffice for learning positive k-juntas

Experimental results suggest the possibility of tighter bounds

The approach effectively tunes networks to target concepts

Abstract

In this paper, we study the tunable quantum neural network architecture in the quantum exact learning framework with access to a uniform quantum example oracle. We present an approach that uses amplitude amplification to correctly tune the network to the target concept. We applied our approach to the class of positive $k$-juntas and found that $O(n^22^k)$ quantum examples are sufficient with experimental results seemingly showing that a tighter upper bound is possible.