Path: utzoo!utgpu!jarvis.csri.toronto.edu!rutgers!tut.cis.ohio-state.edu!gem.mps.ohio-state.edu!ginosko!uunet!dino!ux1.cso.uiuc.edu!ux1.cso.uiuc.edu!m.cs.uiuc.edu!s.cs.uiuc.edu!mehra
From: mehra@s.cs.uiuc.edu
Newsgroups: comp.ai.neural-nets
Subject: Re: Do Higher Order Neurons exist ?
Message-ID: <218600005@s.cs.uiuc.edu>
Date: 24 Oct 89 16:32:46 GMT
References: <384@cs.columbia.edu>
Lines: 24
Nf-ID: #R:cs.columbia.edu:384:s.cs.uiuc.edu:218600005:000:1118
Nf-From: s.cs.uiuc.edu!mehra    Oct 21 10:47:00 1989


? "Are there neurons in  the real brain that support the current research
?  on higher order networks ? "
?
?I'm puzzled with the difficulty to implement simple nets capable of outputting
?a continuous quantity  proportional to the product of its inputs. Even in the
?simpler form (multiplying X and Y to produce K.Z for some K in R), this 
?problem has taken hours in a back-prop simulator, yielding very poor 

Also important to note is the fact that when "real brain" operations
occur, they are in frequency domain. Anyone with even a smattering of
knowledge about signal processing (like me) knows that multiplication
in time domain is convolution in frequency domain. So, what might
seem like a complex operation (multiplication of numbers) might be
realized rather easily in proper frequency domain circuitry...

Now, of course, what with DSP and all, everyone seems to be using
non-neural hardware for doing this stuff. Maybe someone from analog VLSI
knows the answer.

Of course this is speculative, and it is not saying that this is what
Rumelhart et al. had in mind when they wrote their book.

Pankaj Mehra