Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/155123
Title: Efficient learning through biological neural network-Hebbian learning
Authors: Zhou, Yanpeng
Keywords: Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Issue Date: 2021
Publisher: Nanyang Technological University
Source: Zhou, Y. (2021). Efficient learning through biological neural network-Hebbian learning. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/155123
Abstract: Backpropagation provides new inspiration for neural network training, however, its biological rationality is still questionable. Hebbian learning is a completely unsupervised and feedback-free learning technology, which is a strong contender for biologically feasible alternatives. However, so far, it has neither achieved the high-precision performance of backpropagation nor a simple training process. In this dissertation, we have designed three neural networks based on Hebbian learning, namely PHN, MOR and WLAH. The three Hebbian learning networks are based on the improved Hebbian method, which mainly includes changing the weight update equation, introducing activation thresholds, and increasing the sparsity of the hidden layer. These can effectively implement the Hebbian method through a simple training program. In addition, the improved Hebbian rule reduces the number of training cycles from 1500 to 50. At the same time, it changes training from a two-step process to a one-step process to improve training dynamics. Nevertheless, the three Hebbian learning networks still achieve test performance comparable to backpropagation and advanced algorithms on the MNIST dataset.
URI: https://hdl.handle.net/10356/155123
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
Amended Dissertation ZHOU YANPENG Comments by APO.pdf
  Restricted Access
1.8 MBAdobe PDFView/Open

Page view(s)

35
Updated on May 15, 2022

Download(s)

1
Updated on May 15, 2022

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.