caa a22 4500 469125640 CHVBK 20180323133150.0 cr unu---uuuuu 170328e19920501xx s 000 0 eng 10.1007/BF00925117 doi (NATIONALLICENCE)springer-10.1007/BF00925117 Parallel implementation of neural networks [Elektronische Daten] [K. Wojtek Przytula, Viktor Prasanna, Wei-Ming Lin] This paper presents systematic methods, based on graph theoretic approach, for mapping of neural networks onto mesh connected SIMD arrays. The methods are applicable to a large class of multilayer network models, which can be represented in terms of sparse matrix vector operations. The class of computers, that the mappings are suitable for, encompasses most of the experimental and commercial mesh-connected SIMD arrays of processors. There are three methods described in the paper, one for the case of a processor array, which is larger or equal to the network size and two for the partitioned case, i.e. array smaller than the input data size. The methods are illustrated on an example of a multilayer perceptron with back-propagation learning, which consists ofn nuerons ande synaptic connections. For the first method, the processor array is assumed to be of sizeN×N, whereN 2 ≥n+e, and the required local memory of processors is limited to only a few registers. The implementation of a single iteration of a recall phase according to the method requires 24(N-1) shifts. For this method we have developed a software tool, which generates a sequence of pseudo instructions, such as elemental data shift and arithmetic operations, that implement a given neural network on a given size processor array. For the two partitioned methods, the processor array is of sizeP×P, whereP 2≤n+e, and the local memory in the processors is of sizeO(K). The faster of the two methods requiresO(N 3/P 3 K) time for an iteration of the recall or learning phase. Kluwer Academic Publishers, 1992 Wojtek Przytula K. Hughes Research Labs, 3011 Malibu Canyon Road, 90265, Malibu, CA aut Prasanna Viktor Department of EE-Systems, EEB-244, University of Southern California, 90089-2662, Los Angeles, CA aut Lin Wei-Ming Department of Electrical and Computer Engineering, Mississippi State University, 39762, Mississippi State, MS aut Journal of VLSI signal processing systems for signal, image and video technology Springer Netherlands 4/2-3(1992-05-01), 111-123 0922-5773 4:2-3<111 1992 4 11265 https://doi.org/10.1007/BF00925117 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00925117 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Wojtek Przytula K. Hughes Research Labs, 3011 Malibu Canyon Road, 90265, Malibu, CA aut NATIONALLICENCE 700 1- Prasanna Viktor Department of EE-Systems, EEB-244, University of Southern California, 90089-2662, Los Angeles, CA aut NATIONALLICENCE 700 1- Lin Wei-Ming Department of Electrical and Computer Engineering, Mississippi State University, 39762, Mississippi State, MS aut NATIONALLICENCE 773 0- Journal of VLSI signal processing systems for signal, image and video technology Springer Netherlands 4/2-3(1992-05-01), 111-123 0922-5773 4:2-3<111 1992 4 11265 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer