IEEE International Conference on Neural Networks · 2002 · 18 citations · 7 references
ComputingComputer ScienceHigh-performance ComputingMachine LearningParallel AlgorithmsParallel ComputingData ParallelismNeural NetworksParallel ArchitecturesParallel ComputationParallel Computer ArchitectureParallel Computing SystemsFeedforward Neural NetworksMultilayer NetworksNeural Network ModelingParallel Computing ArchitecturesParallel Machine LearningParallel Neural SimulationSimd ArchitecturesSimd Parallelism
Different massively parallel implementations of multilayer feedforward neural networks are presented and compared on a MasPar MP-1216, a parallel single instruction, multiple data (SIMD) computer with 16384 processors. For multilayer feedforward networks, sustained rates of up to 348 M CPS and 129 M CUPS with backpropagation are obtained, a high mark for general purpose SIMD computers. Emphasis is placed on the problems of mapping neural networks to parallel hardware, on implementation problems in obtaining high propagation rates on a SIMD machine, and on problems with the resulting learning algorithms.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
7
A Theory of Networks for Approximation and Learning
Tomaso Poggio, Federico Girosi · 1989 · 716 citations