Optimization of the structural complexity of artificial neural network for hardware-driven neuromorphic computing application
- Authors
- Udaya Mohanan, Kannan; Cho, Seongjae; Park, Byung-Gook
- Issue Date
- Mar-2023
- Publisher
- SPRINGER
- Keywords
- Hardware neuromorphic systems; Hidden layer; Neural networks; Neuron circuits; Pattern recognition; Singular value decomposition (SVD); Synaptic device
- Citation
- Applied Intelligence, v.53, no.6, pp 6288 - 6306
- Pages
- 19
- Journal Title
- Applied Intelligence
- Volume
- 53
- Number
- 6
- Start Page
- 6288
- End Page
- 6306
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/86181
- DOI
- 10.1007/s10489-022-03783-y
- ISSN
- 0924-669X
1573-7497
- Abstract
- This work focuses on the optimization of the structural complexity of a single-layer feedforward neural network (SLFN) for neuromorphic hardware implementation. The singular value decomposition (SVD) method is used for the determination of the effective number of neurons in the hidden layer for Modified National Institute of Standards and Technology (MNIST) dataset classification. The proposed method is also verified on a SLFN using weights derived from a synaptic transistor device. The effectiveness of this methodology in estimating the reduced number of neurons in the hidden layer makes this method highly useful in optimizing complex neural network architectures for their hardware realization.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - IT융합대학 > 전자공학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/86181)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.