HKUST Library Institutional Repository Banner

HKUST Institutional Repository >
Physics >
PHYS Master Theses  >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1783.1/5371
Title: Dynamics of learning in information processing
Authors: Tong, Yiu Wai
Issue Date: 1999
Abstract: The dynamics of learning in neural networks is a complex problem. Though much progress has been made in on-line learning in the past, they were based on some unrealistic assumptions. For batch learning they were applied only to simple learning rules. Here we use the cavity method to study the dynamics of batch learning of random examples, using the Adaline rule as our starting point. Many results are derived, including the average local fields, correlation functions, the training error and the test error. The theoretical predictions are well supported by simulation results. This method can be applied to any learning rule.
Description: Thesis (M.Phil.)--Hong Kong University of Science and Technology, 1999
xi, 112 leaves : ill. ; 30 cm
HKUST Call Number: Thesis PHYS 1999 Tong
URI: http://hdl.handle.net/1783.1/5371
Appears in Collections:PHYS Master Theses

Files in This Item:

File Description SizeFormat
th_redirect.html0KbHTMLView/Open

All items in this Repository are protected by copyright, with all rights reserved.