Title :
A unifying algorithm/architecture for artificial neural networks
Author :
Kung, S.Y. ; Hwang, J.N.
Author_Institution :
Dept. of Electr. Eng., Princeton Univ., NJ, USA
Abstract :
A generic iterative model is presented for a wide variety of artificial neural networks (ANNs): single-layer feedback networks, multilayer feed-forward networks, hierarchical competitive networks, and hidden Markov models. Unifying mathematical formulations are provided for both the retrieving and learning phases of ANNs. Based on the unifying mathematical formulation, a programmable universal ring systolic array is derived for both phases. It maximizes the strength of VLSI in terms of intensive and pipelined computing and yet circumvents the limitation on communication. Hardware implementation for the processing units based on CORDIC techniques is discussed
Keywords :
artificial intelligence; iterative methods; neural nets; ANNs; CORDIC techniques; VLSI; artificial neural networks; generic iterative model; hidden Markov models; hierarchical competitive networks; intensive computing; learning; multilayer feed-forward networks; pipelined computing; processing units; programmable universal ring systolic array; retrieval; single-layer feedback networks; unifying algorithm/architecture; unifying mathematical formulation; Artificial neural networks; Feedforward neural networks; Feedforward systems; Hidden Markov models; Iterative algorithms; Multi-layer neural network; Neural networks; Neurofeedback; Neurons; Systolic arrays;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on
Conference_Location :
Glasgow
DOI :
10.1109/ICASSP.1989.266976
