DocumentCode :
2286047
Title :
Modeling neural networks on the MPP
Author :
Hicklin, Joe ; Demuth, Howard
Author_Institution :
Dept. of Electr. Eng., Idaho Univ., Moscow, ID, USA
fYear :
1988
fDate :
10-12 Oct 1988
Firstpage :
39
Lastpage :
42
Abstract :
A network of fixed-connection-weight neuronlike elements is simulated on the massively parallel processor (MPP) in two ways. First, the square connectivity matrix of a 128-neuron network is mapped onto the square MPP processor array. This allows a highly parallel simulation in which 128 MPP processors were active at all times. Second, a 128-by-128 array of neurons is mapped onto the 16.384 MPP processors. Here the MPP processor limits neuron connections somewhat, but all MPP processors are active at all times and a large speedup is obtained. The first simulation, based on mathematics (weight matrix), produces a significant speedup but tends to obscure the second faster simulation based on mapping the physics (entire physical description) of the neural network onto the MPP. The authors suggest that alternative mappings onto the MPP should be sought and examined carefully
Keywords :
digital simulation; neural nets; parallel processing; highly parallel simulation; massively parallel processor; mathematics; square connectivity matrix; weight matrix; Fires; Mathematics; Nearest neighbor searches; Network topology; Neural networks; Neurons; Physics;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Frontiers of Massively Parallel Computation, 1988. Proceedings., 2nd Symposium on the Frontiers of
Conference_Location :
Fairfax, VA
Print_ISBN :
0-8186-5892-4
Type :
conf
DOI :
10.1109/FMPC.1988.47410
Filename :
47410
Link To Document :
بازگشت