outram@cernvax.UUCP (Nicholas Outram) (12/12/89)
(This is a reposting as no replies received). Can anyone help me with a Time Delay Neural Network problem ???? I first read about them in Byte magazine, and I sent off for the article. All went well, I seemed to understand the concept of forcing the units to 'discover useful phonetic info .. wherever it occured in the input'. PROBLEMS !! ~~~~~~~~~~~ My problems started when I tried to understand the concept of 'adjusting the time delayed weights by the AVERAGE error in those weights across time'. Now hang on a minute ! Surely most of the time delayed units will yield errors in their weights (since by definition the same acoustic event cannot appear across the phoneme). Ok so most of the weights will need to be made more negative. Some, the ones that have detected the correct acoustic feature, will need the weights to be strengthened ( made more positive ). It seems to me that you have a lot of negative adjustments and few positive adjustments - take the average and you have still have a small, but negative, adjustment. Hence no learning. ---> I think I am missing a very important concept ! <--- Could anyone enlighten me ? Puzzled Netter. ----------------------------------------------------------- slow snail mail: Le Chalet, Le Grand Pre, F-01280, Prevessin, FRANCE. ----------------------------------------------------------- ___________________________________________________________