Feed-Forward Neural Networks

Vector Decomposition Analysis, Modelling and Analog Implementation
Softcover Nachdruck of the original 1. Auflage 1995
ISBN: 978-1-4613-5990-6
Verlag: Springer US

Buch, Englisch, Band 314, 238 Seiten, Format (B × H): 155 mm x 235 mm, Gewicht: 394 g

Reihe: The Springer International Series in Engineering and Computer Science

presents a novel method for the mathematical analysis of neural networks that learn according to the back-propagation algorithm. The book also discusses some other recent alternative algorithms for hardware implemented perception-like neural networks. The method permits a simple analysis of the learning behaviour of neural networks, allowing specifications for their building blocks to be readily obtained.
Starting with the derivation of a specification and ending with its hardware implementation, analog hard-wired, feed-forward neural networks with on-chip back-propagation learning are designed in their entirety. On-chip learning is necessary in circumstances where fixed weight configurations cannot be used. It is also useful for the elimination of most mis-matches and parameter tolerances that occur in hard-wired neural network chips.
Fully analog neural networks have several advantages over other implementations: low chip area, low power consumption, and high speed operation.
is an excellent source of reference and may be used as a text for advanced courses.

Zielgruppe

Research

Autoren/Hrsg.

Annema, Jouke

Fachgebiete

• Technische Wissenschaften Energietechnik | Elektrotechnik Elektrotechnik
• Naturwissenschaften Physik Physik Allgemein Theoretische Physik, Mathematische Physik, Computerphysik
• Technische Wissenschaften Elektronik | Nachrichtentechnik Elektronik Bauelemente, Schaltkreise
• Interdisziplinäres Wissenschaften Wissenschaften: Forschung und Information Kybernetik, Systemtheorie, Komplexe Systeme

Inhaltsverzeichnis

1 Introduction.- 2 The Vector Decomposition Method.- 3 Dynamics of Single Layer Nets.- 4 Unipolar Input Signals in Single-Layer Feed-Forward Neural Networks.- 5 Cross-talk in Single-Layer Feed-Forward Neural Networks.- 6 Precision Requirements for Analog Weight Adaptation Circuitry for Single-Layer Nets.- 7 Discretization of Weight Adaptations in Single-Layer Nets.- 8 Learning Behavior and Temporary Minima of Two-Layer Neural Networks.- 9 Biases and Unipolar Input signals for Two-Layer Neural Networks.- 10 Cost Functions for Two-Layer Neural Networks.- 11 Some issues for f’ (x).- 12 Feed-forward hardware.- 13 Analog weight adaptation hardware.- 14 Conclusions.- Nomenclature.