Required dynamic range and accuracy of electronic synapses for character recognition applications
- 2 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1545-1548 vol.3
- https://doi.org/10.1109/iscas.1992.230204
Abstract
Design requirements of electronic synapses and neurons which are used for printed English character recognition, exclusive-OR, and parity check are investigated. On-chip learning strategies for both digital and analog VLSI neural architectures are also described. Experimental results show that the learning process requires a more-than-twice-higher synapse accuracy than the retrieving process. With current silicon technologies, the separate process strategy of off-chip learning and on-chip retrieving can be appropriate to integrate more synapses and neurons into a limited die area.Keywords
This publication has 6 references indexed in Scilit:
- Practical difficulties to design real-time learning VLSI neural circuitsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A compact and general-purpose neural chip with electrically programmable synapsesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Hardware Annealing in Analog VLSI NeurocomputingPublished by Springer Nature ,1991
- A BiCMOS analog neural network with dynamically updated weightsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- DNNA: A Digital Neural Network ArchitecturePublished by Springer Nature ,1990
- Pulse-density modulation technique in VLSI implementations of neural network algorithmsIEEE Journal of Solid-State Circuits, 1990