Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Obstacle Identification by an Ultrasound Sensor Using Neural Networks Read chapter Read first chapter

1998 | OriginalPaper | Chapter

The Evolution of a Feedforward Neural Network trained under Backpropagation

Authors : D. McLean, Z. Bandar, J. D. O’Shea

Published in: Artificial Neural Nets and Genetic Algorithms

Publisher: Springer Vienna

Included in: Professional Book Archive

Get Access

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

This paper presents a theoretical and empirical analysis of the evolution of a feedforward neural network (FFNN) trained using backpropagation (BP). The results of two sets of experiments axe presented which illustrate the nature of BP’s search through weight space as the network learns to classify the training data. The search is shown to be driven by the initial values of the weights in the output layer of neurons.

previous chapter Improved Center Point Selection for Probabilistic Neural Networks
next chapter Fuzzy Vector Bundles for Classification via Neural Networks
Metadata
Title
The Evolution of a Feedforward Neural Network trained under Backpropagation
Authors
D. McLean
Z. Bandar
J. D. O’Shea
Copyright Year
1998
Publisher
Springer Vienna
Book
Artificial Neural Nets and Genetic Algorithms

Print ISBN: 978-3-211-83087-1

Electronic ISBN: 978-3-7091-6492-1

Copyright Year: 1998

DOI
https://doi.org/10.1007/978-3-7091-6492-1_114