loren@tristan.llnl.gov (Loren Petrich) (10/11/90)
I read in the June(?) issue of _Scientific American_ of the investigations of Donald(?) Alkon into learning in nervous systems and the Neural Net architecture that he had come up with, called DYSTAL. Does anyone have any references on that? I discovered that he had a paper on it in the 1989 IJCNN Conference, vol. 2, but the Berkeley library did not have that volume on hand. Could anyone dig it up for me and give me a summary of it? He had claimed that its performance is superior to backprop; I hope I can see for myself. $$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$ Loren Petrich, the Master Blaster: loren@sunlight.llnl.gov Since this nodename is not widely known, you may have to try: loren%sunlight.llnl.gov@star.stanford.edu