LFD Book Forum  

Go Back   LFD Book Forum > Course Discussions > Online LFD course > Homework 5

Reply
 
Thread Tools Display Modes
  #1  
Old 10-30-2012, 07:36 PM
drudru drudru is offline
Junior Member
 
Join Date: Oct 2012
Posts: 2
Default Lecture 10 : Perceptron Logic OR gate

Hello,

In Lecture 10 - slides 9-11:

Shouldn't the bias be -0.5 (some number < 0) for the OR() perceptron?
aka w = (-0.5,1,1). Otherwise an input of (0,0) on (1.5,1,1) would be at 1.5 or True.

AND() is w = (-1.5,1,1), and that is consistent with SIGN as the threshold.

I searched the slides and I couldn't find a definition of the perceptron threshold function other than SIGN.

Dru
Reply With Quote
  #2  
Old 10-30-2012, 08:55 PM
yaser's Avatar
yaser yaser is offline
Caltech
 
Join Date: Aug 2009
Location: Pasadena, California, USA
Posts: 1,478
Default Re: Lecture 10 : Perceptron Logic OR gate

Quote:
Originally Posted by drudru View Post
Hello,

In Lecture 10 - slides 9-11:

Shouldn't the bias be -0.5 (some number < 0) for the OR() perceptron?
aka w = (-0.5,1,1). Otherwise an input of (0,0) on (1.5,1,1) would be at 1.5 or True.

AND() is w = (-1.5,1,1), and that is consistent with SIGN as the threshold.

I searched the slides and I couldn't find a definition of the perceptron threshold function other than SIGN.
The binary convention we use is \pm 1 rather than 0/1. With this convention, the above values work out.
__________________
Where everyone thinks alike, no one thinks very much
Reply With Quote
  #3  
Old 10-30-2012, 11:17 PM
drudru drudru is offline
Junior Member
 
Join Date: Oct 2012
Posts: 2
Default Re: Lecture 10 : Perceptron Logic OR gate

Ah, thank you.
Reply With Quote
Reply

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT -7. The time now is 01:29 AM.


Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2021, Jelsoft Enterprises Ltd.
The contents of this forum are to be used ONLY by readers of the Learning From Data book by Yaser S. Abu-Mostafa, Malik Magdon-Ismail, and Hsuan-Tien Lin, and participants in the Learning From Data MOOC by Yaser S. Abu-Mostafa. No part of these contents is to be communicated or made accessible to ANY other person or entity.