A Nonsynaptic Memory Based Neural Network for Hand-Written Digit Classification Using an Explainable Feature Extraction Method

Faramarz Faghihi, Siqi Cai, Ahmed Moustafa, Hany Alashwal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep learning methods have been developed for handwritten digit classification. However, these methods work as black-boxes' and need large training data. In this study, an explainable feature extraction method is developed for handwritten digit classification. The features of the digit image include horizontal, vertical, and orthogonal lines as well as full or semi-circles. In our proposed method, such features are extracted using 10 neurons as computational units. Specifically, the neurons store the features through network training and store them inside the neurons in a non-synaptic memory manner. Following that, the trained neurons are used for the retrieval of information from test images to assign them to digit categories. Our method shows an accuracy of 75 % accuracy using 0.016 % of the training data and achieves a high accuracy of 86 % using one epoch of whole training data of the MNIST dataset. To the best of our knowledge, this is the first model that stores information inside a few single neurons (i.e., non-synaptic memory) instead of storing the information in synapses of connected feed-forward layers. Due to enabling single neurons to compute individually, it is expected that such a class of neural networks can be combined with synaptic memory architectures that we expect to show higher performance compared to traditional neural networks.

Original languageEnglish
Title of host publicationICISDM 2022 - 2022 6th International Conference on Information System and Data Mining
PublisherAssociation for Computing Machinery
Pages69-75
Number of pages7
ISBN (Electronic)9781450396257
DOIs
Publication statusPublished - May 27 2022
Event6th International Conference on Information System and Data Mining, ICISDM 2022 - Virtual, Online, United States
Duration: May 27 2022May 29 2022

Publication series

NameACM International Conference Proceeding Series

Conference

Conference6th International Conference on Information System and Data Mining, ICISDM 2022
Country/TerritoryUnited States
CityVirtual, Online
Period5/27/225/29/22

Keywords

  • classification
  • explainable AI
  • neural network
  • non-synaptic memory

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'A Nonsynaptic Memory Based Neural Network for Hand-Written Digit Classification Using an Explainable Feature Extraction Method'. Together they form a unique fingerprint.

Cite this