Text classification in memristor-based spiking neural networks. Issue 1 (1st March 2023)

• Record Type: Journal Article
• Authors: Huang, Jinqi; Serb, Alexantrou; Stathopoulos, Spyros; Prodromakis, Themis
• Is Part Of: Neuromorphic computing and engineering. Volume 3:Issue 1(2023)
• Publication Date: 2023-03-01
• Subjects: text classification -- sentiment analysis -- natural language processing -- spiking neural networks -- memristors -- online learning -- offline classification; Neural networks (Computer science) -- Periodicals; Neural computers -- Periodicals; Neuromorphics -- Periodicals; 006.3
• DOI: 10.1088/2634-4386/acb2f0
• Languages: English
• ISSNs: 2634-4386

Abstract

Abstract: Memristors, emerging non-volatile memory devices, have shown promising potential in neuromorphic hardware designs, especially in spiking neural network (SNN) hardware implementation. Memristor-based SNNs have been successfully applied in a wide range of applications, including image classification and pattern recognition. However, implementing memristor-based SNNs in text classification is still under exploration. One of the main reasons is that training memristor-based SNNs for text classification is costly due to the lack of efficient learning rules and memristor non-idealities. To address these issues and accelerate the research of exploring memristor-based SNNs in text classification applications, we develop a simulation framework with a virtual memristor array using an empirical memristor model. We use this framework to demonstrate a sentiment analysis task in the IMDB movie reviews dataset. We take two approaches to obtain trained SNNs with memristor models: (1) by converting a pre-trained artificial neural network (ANN) to a memristor-based SNN, or (2) by training a memristor-based SNN directly. These two approaches can be applied in two scenarios: offline classification and online training. We achieve the classification accuracy of 85.88% by converting a pre-trained ANN to a memristor-based SNN and 84.86% by training the memristor-based SNN directly, given that the baseline training accuracy of the equivalent ANN is 86.02%. We conclude that it is possible to achieve similar classification accuracy in simulation from ANNs to SNNs and from non-memristive synapses to data-driven memristive synapses. We also investigate how global parameters such as spike train length, the read noise, and the weight updating stop conditions affect the neural networks in both approaches. This investigation further indicates that the simulation using statistic memristor models in the two approaches presented by this paper can assist the exploration of memristor-based SNNs in natural language processing tasks.