Xref: utzoo sci.electronics:3560 comp.ai:2099 comp.ai.neural-nets:182
Path: utzoo!attcan!uunet!husc6!bloom-beacon!tut.cis.ohio-state.edu!mailrus!ames!pasteur!ucbvax!decwrl!labrea!glacier!jbn
From: jbn@glacier.STANFORD.EDU (John B. Nagle)
Newsgroups: sci.electronics,comp.ai,comp.ai.neural-nets
Subject: Re: Sigmoid transfer function
Message-ID: <17621@glacier.STANFORD.EDU>
Date: 8 Aug 88 03:00:35 GMT
References: <1945@aecom.YU.EDU> <17615@glacier.STANFORD.EDU> <25516@ucbvax.BERKELEY.EDU>
Reply-To: jbn@glacier.UUCP (John B. Nagle)
Organization: Stanford University
Lines: 10

In article <25516@ucbvax.BERKELEY.EDU> munro@icsia.UUCP (Paul Munro) writes:
>
>Try this one :   f(x) = x / (1 + |x|)
>

      The graph looks OK, although some scaling is needed to make it comparable
to the sigmoid.  Someone should try it in one of the popular neural net
simulators and see how the results change.

					John Nagle