An adaptable Boolean net trainable to control a computing robot

Journal Article · Mon Mar 22 00:00:00 EST 1999 · AIP Conference Proceedings

DOI:https://doi.org/10.1063/1.58263· OSTI ID:21205281

Lauria, F E; Prevete, R; Milo, M; Visco, S ^[1]

---

1. Dipartimento di Scienze Fisiche dell' Universita di Napoli and Istituto Nazionale di Fisica della Materia, Mostra D'Oltremare, Pad. 19, I-80125 Naples (Italy)

We discuss a method to implement in a Boolean neural network a Hebbian rule so to obtain an adaptable universal control system. We start by presenting both the Boolean neural net and the Hebbian rule we have considered. Then we discuss, first, the problems arising when the latter is naively implemented in a Boolean neural net, second, the method consenting us to overcome them and the ensuing adaptable Boolean neural net paradigm. Next, we present the adaptable Boolean neural net as an intelligent control system, actually controlling a writing robot, and discuss how to train it in the execution of the elementary arithmetic operations on operands represented by numerals with an arbitrary number of digits.

• OSTI ID: 21205281
• Journal Information: AIP Conference Proceedings, Vol. 465, Issue 1; Conference: CASYS'98: 2. international conference on computing anticipatory systems, Liege (Belgium), 10-14 Aug 1998; Other Information: DOI: 10.1063/1.58263; (c) 1999 American Institute of Physics; Country of input: International Atomic Energy Agency (IAEA); ISSN 0094-243X
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
ALGEBRA
ARTIFICIAL INTELLIGENCE
CONTROL
CONTROL SYSTEMS
LEARNING
NEURAL NETWORKS
ROBOTS
TRAINING