colwell@mfci.UUCP (Robert Colwell) (02/02/90)
Speaking of naive neural net inquiries, here's mine -- does anybody have any solutions to the extra problems posed in Vol III of the PDP series by Rumelhart and McClelland? The kind you feed into the programs they supplied on the floppies in the back? Bob Colwell ..!uunet!mfci!colwell Multiflow Computer or colwell@multiflow.com 31 Business Park Dr. Branford, CT 06405 203-488-6090
ssingh@watserv1.waterloo.edu ($anjay "lock-on" $ingh - Indy Studies) (02/05/90)
Another question that has gone unanswered since I began studying NNs. I have been to two tutorials, one by Rumelhart and Sejnowski, and the other by Hinton, and both imply that all the mathematics needed to make an original contribution to NN work is simple calculus. Is this really the case? If not, where is a good primer for preparing a reader from a mathematical standpoint to model biological networks. Anyone who has seen Neural and Brain Modelling (R.J. Macgregor, 1987 Academic Press) would agree that there is some daunting mathematics in there. Thank you. -- $anjay "lock-on" $ingh ssingh@watserv1.waterloo.edu "A modern-day warrior, mean mean stride, today's Tom Sawyer, mean mean pride." !being!mind!self!cogsci!AI!think!nerve!parallel!cybernetix!chaos!fractal!info!
bill@boulder.Colorado.EDU (02/06/90)
In article <958@watserv1.waterloo.edu> ssingh@watserv1.waterloo.edu ($anjay "lock-on" $ingh - Indy Studies) writes: >Another question that has gone unanswered since I began studying NNs. I have >been to two tutorials, one by Rumelhart and Sejnowski, and the other by >Hinton, and both imply that all the mathematics needed to make an >original contribution to NN work is simple calculus. Is this really >the case? [ . . . ] Well, the answer is, it depends on the kind of contribution you want to make. If you want to do theoretical work on questions like "Are neural networks computationally equivalent to Turing machines?" or "For what problems is a Boltzmann machine guaranteed to converge on the best solution?", then it helps to have a pretty strong mathematical background. However, there are a number of extremely important open questions for which ingenuity, intuition, and hard work are likely to mean more than mathematical knowledge. For example: a large portion of the PDP books (edited by Rumelhart & McClelland) is devoted to setting up simple network models of various psychological processes and examining their behavior. A lot more work can be done in that direction, probably using little more than back-prop or competitive learning. Perhaps the most important basic question in the whole domain is the extent to which massively distributed parallelism can make up for crude and simplistic algorithms, and that is something which probably can only be investigated by looking at lots of examples. -- Bill Skaggs