A Survey of Classical And Quantum Sequence Models

TL;DR

This survey reviews classical and quantum sequence models, introduces hybrid quantum-classical approaches, and compares their performance in text and image classification tasks, highlighting recent advances and potential benefits of quantum methods.

Contribution

The paper provides a comprehensive survey of quantum sequence models, implements quantum hybrid transformers, and compares quantum and classical models to evaluate their effectiveness.

Findings

Quantum self-attention improves accuracy in classification tasks.

Quantum models converge faster with positional encoding.

Hybrid quantum-classical models show promising performance.

Abstract

Our primary objective is to conduct a brief survey of various classical and quantum neural net sequence models, which includes self-attention and recurrent neural networks, with a focus on recent quantum approaches proposed to work with near-term quantum devices, while exploring some basic enhancements for these quantum models. We re-implement a key representative set of these existing methods, adapting an image classification approach using quantum self-attention to create a quantum hybrid transformer that works for text and image classification, and applying quantum self-attention and quantum recurrent neural networks to natural language processing tasks. We also explore different encoding techniques and introduce positional encoding into quantum self-attention neural networks leading to improved accuracy and faster convergence in text and image classification experiments. This paper also performs a comparative analysis of classical self-attention models and their quantum counterparts, helping shed light on the differences in these models and their performance.