詳情
識別號
stcompfyp:111
題名
A hybrid algorithm based on backpropagation with magnified gradient function guided by adaptive particle swarm optimization in neural network training
作品類型
Final Year Project/Work
系列 / 集 / 庫
S&T Best Computing Projects
創建者
Lui, Wing On (creator)
Ng, Sin Chun Vanessa 吳倩珍 (supervisor)
學院 / 部門
School of Science and Technology (S&T) 
課程
Bachelor of Science with Honours in Computing
日期
2012
摘要
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.
資料類型
PDF
語言
English
資料描述
1 page.
獎項
1st runner-up (undergraduate section), Student Paper Contest, 2012 (IEEE(HK), Institute of Electrical and Electronics Engineers Hong Kong Section)
關鍵字
neural networks; algorithms; Backpropagation (BP) with magnified gradient function (MGFProp); Adaptive particle swarm optimization (APSO); Magnified gradient function (MGF)
存取限制
Public Access
固定連結