A Survey of Classical And Quantum Sequence Models
This is an incremental survey and implementation paper that compares classical and quantum sequence models for researchers in quantum machine learning.
The paper surveys classical and quantum neural sequence models, re-implements existing quantum methods to create a hybrid transformer for text/image classification, and introduces positional encoding to quantum self-attention, leading to improved accuracy and faster convergence in experiments.
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.