Towards interpretable quantum machine learning via single-photon quantum walks

TL;DR

This paper introduces a quantum-enhanced reinforcement learning model using single-photon quantum walks to improve interpretability and decision-making capabilities in artificial intelligence.

Contribution

It presents a novel variational method to quantize projective simulation with quantum walks, enhancing interpretability and leveraging quantum interference for AI decision processes.

Findings

Quantum walks enable transfer learning beyond classical limits

Quantum interference improves decision-making capabilities

The model offers insights into quantum effects in AI interpretability

Abstract

Variational quantum algorithms represent a promising approach to quantum machine learning where classical neural networks are replaced by parametrized quantum circuits. However, both approaches suffer from a clear limitation, that is a lack of interpretability. Here, we present a variational method to quantize projective simulation (PS), a reinforcement learning model aimed at interpretable artificial intelligence. Decision making in PS is modeled as a random walk on a graph describing the agent's memory. To implement the quantized model, we consider quantum walks of single photons in a lattice of tunable Mach-Zehnder interferometers trained via variational algorithms. Using an example from transfer learning, we show that the quantized PS model can exploit quantum interference to acquire capabilities beyond those of its classical counterpart. Finally, we discuss the role of quantum interference for training and tracing the decision making process, paving the way for realizations of interpretable quantum learning agents.