This paper discusses digital electronic VLSI architectures for emulating neural networks. The major advantage of digital implementation is its flexibility, which, because of “Amdahl’s Law,” is more valuable than raw speed. As an example of a digital architecture, Adaptive Solution’s CNAPS1, architecture is discussed in detail. CNAPS consists of a single-instruction, multiple-data (SIMD) or "data parallel” array of simple DSP-like processor nodes. By using low-precision arithmetic, an optimized processor architecture, and simple broadcast communication, many processors can fit on a one silicon chip, thus allowing cost-effective, high-performance computation for image processing and pattern recognition applications.

The last half of the paper discusses mapping several algorithms to the CNAPS architecture. Algorithms discussed include back-propagation, Fourier transforms, JPEG image compression, and convolution.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Dan Hammerstrom, Dan Hammerstrom, } "Digital electronic neural networks", Proc. SPIE 10277, Adaptive Computing: Mathematics, Electronics, and Optics: A Critical Review, 1027707 (1 March 1994); doi: 10.1117/12.171196; https://doi.org/10.1117/12.171196


Analog VLSI neural systems: trends and challenges
Proceedings of SPIE (April 05 1995)
High-speed low-power analog ASICs for a 3D neuroprocessor
Proceedings of SPIE (March 27 1995)
Optimization of input-constrained systems
Proceedings of SPIE (May 28 2009)
Bearing monitoring
Proceedings of SPIE (July 19 2001)

Back to Top