Simulation of heterogeneous neural networks on serial and parallel machines

Book · Tue Jan 01 04:00:00 EST 1991

OSTI ID:5094190

Lange, T E

There has recently been a tremendous rebirth of interest in neural networks, ranging from distributed and localist spreading-activation networks to semantic networks with symbolic marker-passing. Ideally these networks would be encoded in dedicated massively-parallel hardware that directly implements their functionality. Cost and flexibility concerns, however, necessitate the use of general-purpose machines to simulate neural networks, especially in the research stages in which various models are being explored and tested. Issues of a simulation's timing and control become more critical when models are made up of heterogeneous networks in which nodes have different processing characteristics and cycling rates or which are made up of modular, interacting sub-networks. The authors have developed a simulation environment to create, operate, and control these types of connectionist networks. This paper describes how massively-parallel heterogeneous networks are simulated on serial machines as efficiently as possible, how large- scale simulations could be handled on current SIMD parallel machines, and outlines how the simulator could be implemented on its ideal hardware, a large-scale MIMD parallel machine.

• OSTI ID: 5094190
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
COMPUTER ARCHITECTURE
COMPUTERIZED SIMULATION
NEURAL NETWORKS
PARALLEL PROCESSING
PROGRAMMING
SIMULATION