Title :
Neural-style microsystems that learn
Author :
Alspector, Joshua
Author_Institution :
Bellcore, Red Bank, NJ, USA
Abstract :
The basic operation of biological and electronic (artificial) neural networks (NNs) is examined. Learning by NNs is discussed, covering supervised learning, particularly back-propagation, and unsupervised and reinforcement learning. The use of VLSI implementation to speed learning is considered briefly. Applications of neural-style learning chips to pattern recognition, data compression, optimization, and expert systems is discussed. Problem areas and issues for further research are addressed.<>
Keywords :
VLSI; digital signal processing chips; learning systems; neural nets; VLSI; back-propagation; data compression; expert systems; learning; neural networks; neural-style learning chips; optimization; pattern recognition; Artificial neural networks; Data compression; Expert systems; Pattern recognition; Supervised learning; Very large scale integration;
Journal_Title :
Communications Magazine, IEEE
