Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > alt.language.artificial > #8 > unrolled thread

Preceptors and wieght or Bias

Started byruben safir <ruben@mrbrklyn.com>
First post2017-03-27 21:49 -0400
Last post2017-03-27 21:51 -0400
Articles 2 — 1 participant

Back to article view | Back to alt.language.artificial


Contents

  Preceptors and wieght or Bias ruben safir <ruben@mrbrklyn.com> - 2017-03-27 21:49 -0400
    Re: Preceptors and wieght or Bias ruben safir <ruben@mrbrklyn.com> - 2017-03-27 21:51 -0400

#8 — Preceptors and wieght or Bias

Fromruben safir <ruben@mrbrklyn.com>
Date2017-03-27 21:49 -0400
SubjectPreceptors and wieght or Bias
Message-ID<obcff3$510$1@reader1.panix.com>
When I have a preceptor, shouldn't I have a weighted bias that is added
to the system?  How is that done.  I'm reading this

https://liucs.net/cs691s17/perceptrons.html

and trying to coralate it with pg 728 of Stuart J. Russell and Peter
Norvig - 3rd edition

[toc] | [next] | [standalone]


#9

Fromruben safir <ruben@mrbrklyn.com>
Date2017-03-27 21:51 -0400
Message-ID<obcfiq$510$2@reader1.panix.com>
In reply to#8
On 03/27/2017 09:49 PM, ruben safir wrote:
> When I have a preceptor, shouldn't I have a weighted bias that is added
> to the system?  How is that done.  I'm reading this
> 
> https://liucs.net/cs691s17/perceptrons.html
> 
> and trying to coralate it with pg 728 of Stuart J. Russell and Peter
> Norvig - 3rd edition
> 

To quote the text:

Just as in linear regression models, each unit has a dummy input a0 = 1
with an associated weight w0,j .

[toc] | [prev] | [standalone]


Back to top | Article view | alt.language.artificial


csiph-web