Title :
Simulation of associative neural networks
Author :
Zhu, Shaojuan ; Hammerstrom, Dan
Abstract :
The human brain is far superior to a modern computer in its ability to do associative recall. Many theorists believe that one of the important functions of primate neocortex is "associative memory". Palm\´s network (Palm et al., 1997) is one of the most powerful associative memory models available. To study variations of this basic model, we have built a multiprocessor based Palm simulator that executes on our Beowulf cluster and supercomputers at NASA. We have also created a spiking version that adds temporal information to the model and is more biologically plausible. Experimental results are summarized, and the problems solved are also discussed.
Keywords :
associative processing; content-addressable storage; digital simulation; multiprocessing systems; neural nets; workstation clusters; Beowulf cluster; NASA; associative memory; associative neural network simulation; associative recall; experimental results; multiprocessor based Palm simulator; primate neocortex; spiking; supercomputers; temporal information; Associative memory; Associative processing; Biological neural networks; Computer science; Contracts; Educational institutions; Impedance matching; NASA; Neural networks; Neurons;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1198953