Path: utzoo!attcan!uunet!seismo!esosun!ucsdhub!sdcsvax!amos!joe From: joe@amos.ling.ucsd.edu (Shadow) Newsgroups: comp.ai.neural-nets Subject: Re: Learning arbitrary transfer functio Message-ID: <5572@sdcsvax.UCSD.EDU> Date: 29 Nov 88 20:30:23 GMT References: <399@uvaee.ee.virginia.EDU> <163400002@inmet> Sender: nobody@sdcsvax.UCSD.EDU Reply-To: joe@amos.UUCP (Shadow) Organization: Univ. of Calif., San Diego Lines: 49 In article <163400002@inmet> ryer@inmet.UUCP writes: >> So, how do human's learn non linear functions ? >> >> : you learn that x^2, for instance, is X times X. >> >> And how about X times Y ? How do humans learn that ? >> >> : you memorize it, for single digits, and >> : for more than a single digit, you multiply streams >> of digits together in a carry routine. >Although my knowledge of neural nets is limited, I won't buy what is >written above. Most persons can, for example, throw a baseball more >or less at the target in spite of gravity. This requires a non-linear >calculation. This is not done via multiplication tables. Sure it is >done by "experience", but so are neural network calculations. Hmm. I'm no expert on human learning, but I don't buy what's written above. When I throw a baseball off the top of a ten-story building, I am very bad at hitting that at which I aimed (e.g., students). This would lead me to theorize that I have not learned a non-linear relationship. All of this aside, I must note that the original article was misinterpreted. That was unfortunate, as I was theorizing on ways to improve generalized learning of non-linear mathematical relationships for data outside of the training domain... results in this area were usally fairly dismal in the experiments which I conducted. Ideas: 1. how about linear units on the output layer ? (Idea care of Jeff Elman, ICS, CRL) 2. sub-networks trained for sub-tasks. (sub-networks mentioned to me in passing by Jeff Elman, ICS,CRL) I welcome comments, and actually, I would really like to hear from people who are experts on human learning. This topic is obviously too hot for me to handle. (feel free to send mail) =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= = - = = "But why not play god ? " - joe@amos.ling.ucsd.edu = = - un-named geneticist - = = - = =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=