🚀 go-pugleaf

RetroBBS NetNews Server

Inspired by RockSolid Light RIP Retro Guy

Article View: sci.electronics
Article #19562

Re: Sigmoid transfer function

#19562
From: John B. Nagle
Date: Mon, 08 Aug 1988 03:00
10 lines
863 bytes
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
Technical Details
Message-ID: <17621@glacier.STANFORD.EDU>
Path: arc1-ca.pugleaf.net!utzoo!attcan!uunet!husc6!bloom-beacon!tut.cis.ohio-state.edu!mailrus!ames!pasteur!ucbvax!decwrl!labrea!glacier!jbn
References: <1945@aecom.YU.EDU> <17615@glacier.STANFORD.EDU> <25516@ucbvax.BERKELEY.EDU>

Show Full Headers
Complete Article Headers
Path: arc1-ca.pugleaf.net!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