ReverbaProp: simultaneous learning of credit and weight

Robert Chris Lacher; Douglas Alan Klotter

doi:10.1117/12.205159

6 April 1995 ReverbaProp: simultaneous learning of credit and weight

Robert Chris Lacher, Douglas Alan Klotter

Proceedings Volume 2492, Applications and Science of Artificial Neural Networks; (1995) https://doi.org/10.1117/12.205159
Event: SPIE's 1995 Symposium on OE/Aerospace Sensing and Dual Use Photonics, 1995, Orlando, FL, United States

Abstract

We introduce a supervised learning method for feed-forward networks that solves the credit assignment problem for error in concert with solving the error reduction problem normally associated with methods such as backpropagation. The method reverberates between forward and reverse activations of the network. Forward activation using an exemplar computes output for each node in the network using the connection weights as usual. Reverse activation using output error as input computes local error at each node using reverse weights, or responsibilities, on the reverse connections. Reverse-reverse activation (the same as forward activation with linear output functions) using reverse output error as input computes local reverse error at each node. Once local error and local reverse error have been assigned to each node, weights and responsibilities are modified using the standard delta rule and local error and local reverse error, respectively. The method relies on convergence toward an optimal set of responsibilities for reverse error distribution in concert with convergence toward an optimal set of weights, and thus avoids calculation of nonlinear terms in the usual error backpropagation method. Thus the method is free of derivative evaluations, and by allowing credit assignment to optimize simultaneously with error reduction, it promotes clustering of responsibility among the nodes.

Citation Download Citation

Robert Chris Lacher and Douglas Alan Klotter "ReverbaProp: simultaneous learning of credit and weight", Proc. SPIE 2492, Applications and Science of Artificial Neural Networks, (6 April 1995); https://doi.org/10.1117/12.205159

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Error analysis

Binary data

Machine learning

Network architectures

Computer science

Computing systems

Neural networks

Show All Keywords

Keywords/Phrases

Search In:

Publication Years