Details
Record ID
stcompfyp:111
Title
A hybrid algorithm based on backpropagation with magnified gradient function guided by adaptive particle swarm optimization in neural network training
Type of Work
Final Year Project/Work
Collection
S&T Best Computing Projects
Contributor
Lui, Wing On (creator)
Ng, Sin Chun Vanessa 吳倩珍 (supervisor)
School / Unit
School of Science and Technology (S&T) 
Program
Bachelor of Science with Honours in Computing
Date
2012
Abstract
This project aims to design a hybrid algorithm of MGFProp and APSO and investigate its performance, in terms of learning speed and global optimality. In this project, we use APSO to perform global searches for good starting positions for MGFProp to perform local searches.
Type of Resource
PDF
Language
English
Physical Description
1 page.
Awards
1st runner-up (undergraduate section), Student Paper Contest, 2012 (IEEE(HK), Institute of Electrical and Electronics Engineers Hong Kong Section)
Keywords
neural networks; algorithms; Backpropagation (BP) with magnified gradient function (MGFProp); Adaptive particle swarm optimization (APSO); Magnified gradient function (MGF)
Access Eligibility
Public Access
Permanent Link