Properties of a Batch Training Algorithm for Feedforward Networks |
| |
Authors: | Melvin D. Robinson Michael T. Manry Sanjeev S. Malalur Changhua Yu |
| |
Affiliation: | 1.Department of Electrical Engineering,University of Texas at Tyler,Tyler,USA;2.Department of Electrical Engineering,University of Texas at Arlington,Arlington,USA;3.O-Geo Well LLC,Fort Worth,USA;4.Abbott Labs,Chicago,USA |
| |
Abstract: | We examine properties for a batch training algorithm known as the output weight optimization–hidden weight optimization (OWO–HWO). Using the concept of equivalent networks, we analyze the effect of input transformation on BP. We introduce new theory of affine invariance and partial affine invariance for neural networks and prove this property for OWO–HWO. Finally, we relate HWO to BP and show that every iteration of HWO is equivalent to BP applied to whitening transformed data. Experimental results validate the connection between OWO–HWO and OWO–BP. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|