𝔖 Bobbio Scriptorium
✦   LIBER   ✦

A symbolic interpretation for back-propagation networks

✍ Scribed by P. Magrez; A. Rousseau

Publisher
John Wiley and Sons
Year
1992
Tongue
English
Weight
974 KB
Volume
7
Category
Article
ISSN
0884-8173

No coin nor oath required. For personal study only.

✦ Synopsis

Two main problems for the neural network (NN) paradigm are discussed: the output value interpretation and the symbolic content of the connection matrix. In this article, we construct a solution for a very common architecture of pattern associators: the backpropagation networks. First, we show how Zadeh's possibility theory brings a formal structure to the output interpretation. Properties and practical applications of this theory are developed. Second, a symbolic interpretation for the connection matrix is proposed by designing of an algorithm. By accepting the NN training examples as input this algorithm produces a set of implication rules. These rules accurately model the NN behavior. Moreover, they allow to understand it, especially in the cases of generalization or interference.

πŸ“œ SIMILAR VOLUMES

A new method for efficient symbolic prop
A new method for efficient symbolic propagation in discrete Bayesian networks
✍ Castillo, Enrique; GutiοΏ½rrez, JosοΏ½ Manuel; Hadi, Ali S. πŸ“‚ Article πŸ“… 1996 πŸ› John Wiley and Sons 🌐 English βš– 993 KB

This paper presents a new efficient method for uncertainty propagation in discrete Bayesian networks in symbolic, as opposed to numeric, form, when considering some of the probabilities of the Bayesian network as parameters. The algebraic structure of the conditional probabilities of any set of node

An adaptive training algorithm for back
An adaptive training algorithm for back propagation networks
✍ L.-W. Chan; F. Fallside πŸ“‚ Article πŸ“… 1987 πŸ› Elsevier Science 🌐 English βš– 628 KB

The effect of the coefficients used in the conventional back propagation algorithm on training connectionist models is discussed, using a vowel recognition task in speech processing as an example. Some weaknesses of the use of fixed coefficients are described and an adaptive algorithm using variable

Back-propagation neural network for long
Back-propagation neural network for long-term tidal predictions
✍ Tsong-Lin Lee πŸ“‚ Article πŸ“… 2004 πŸ› Elsevier Science 🌐 English βš– 261 KB

During the recent years, the availability of accurate ocean tide models has become increasingly important, as tides are the main contributor to disposal and movement of sediments, tracers and pollutants, and to a whole range of offshore applications in engineering, environmental observations, explor

A study of back-error propagation networ
A study of back-error propagation networks for a trainable tactile pattern classifier
✍ Marcus Thint; Paul P. Wang; Jack Rebman πŸ“‚ Article πŸ“… 1992 πŸ› Elsevier Science 🌐 English βš– 975 KB

## Current robotic taction applications have largely been limited to presence~absence detection via "simple touch" or the use of force-torque sensors. Although artificial tactile sensors have been developed, advanced industrial applications have not matured due to time and resource constraints in ma