Bias node in BP

Started by yagyavrat, Mar 11 2013 05:36 AM

back propagation

Old topic!
Guest, the last post of this topic is over 60 days old and at this point you may not reply in this topic. If you wish to continue this conversation start a new topic.

You cannot reply to this topic

1 reply to this topic

#1 yagyavrat Members - Reputation: 101

0Likes

Posted 11 March 2013 - 05:36 AM

Hi All,

I am new to BP, I am started learning it recently, unable to get the use of Bias node in BP...

Please explain it simply...

Thank You..

Sponsor:

#2 Tournicoti Members - Reputation: 489

0Likes

Posted 11 March 2013 - 10:43 AM

Hello

By BP, what do you mean please?

~~Are you talking about back-propagation ?~~ Yes you are, I didn't see your tag

If so, the bias is not related to back-propagation, but to Mc Culloch & Pitts model.

Any network model that use Mc Culloch & Pitts model must use a bias, as it is described in any good explanation.

The bias permit to shift the activation (or transfert) function, along x axis.

The common way to implement it is to add a constant input (1 or -1 usually) in input vector of each node and make its weight (i.e the bias) evolve like any other weight.

An analogy in 2D : the bias is like c in the line equation a.x+b.y+c=0

Edited by Tournicoti, 11 March 2013 - 03:04 PM.

Back to For Beginners

Old topic!
Guest, the last post of this topic is over 60 days old and at this point you may not reply in this topic. If you wish to continue this conversation start a new topic.