Title :
Electronic implementation of neuromorphic systems
Author_Institution :
Lincoln Lab., MIT, Lexington, MA, USA
Abstract :
The electronic implementation of neuromorphic systems requires technologies well matched to the functions of storage and the computation of sums of products. Additional requirements are low-power, high fan-out capability and high-density interconnect. Massive parallelism and redundancy mitigate the accuracy limitations of analog circuits and force consideration of analog and analog-digital components for network realization. Adaptive neuromorphic networks have the potential for self-organization and learning in speech and image understanding systems requiring minimal human intervention
Keywords :
VLSI; adaptive systems; learning systems; neural nets; pattern recognition; speech recognition; VLSI; adaptive systems; analog circuits; analog-digital components; electronic implementation; fan-out capability; high-density interconnect; image understanding systems; learning; neuromorphic systems; parallelism; redundancy; self-organization; speech understanding; Circuit faults; Design engineering; Integrated circuit modeling; Multidimensional systems; Neuromorphics; Neurons; Power engineering and energy; Power engineering computing; Throughput; Voltage;
Conference_Titel :
Custom Integrated Circuits Conference, 1988., Proceedings of the IEEE 1988
Conference_Location :
Rochester, NY
DOI :
10.1109/CICC.1988.20836
