Quantum RNNs and LSTMs Through Entangling and Disentangling Power of Unitary Transformations

TL;DR

This paper introduces a quantum RNN and LSTM framework based on the entangling and disentangling properties of unitary transformations, aiming to improve quantum circuit design for real-world tasks.

Contribution

It proposes a novel quantum RNN/LSTM model leveraging entangling power of unitaries to enhance information retention and forgetting, guiding better quantum circuit design.

Findings

Entangling power correlates with information retention.

Disentangling power relates to information forgetting.

Framework guides quantum circuit optimization.

Abstract

In this paper, we present a framework for modeling quantum recurrent neural networks (RNNs) and their enhanced version, long short-term memory (LSTM) networks using the core ideas presented by Linden et al. (2009), where the entangling and disentangling power of unitary transformations is investigated. In particular, we interpret entangling and disentangling power as information retention and forgetting mechanisms in LSTMs. Thus, entanglement emerges as a key component of the optimization (training) process. We believe that, by leveraging prior knowledge of the entangling power of unitaries, the proposed quantum-classical framework can guide the design of better-parameterized quantum circuits for various real-world applications.