Misplaced Pages

Talk:Boltzmann machine

Article snapshot taken from Wikipedia with creative commons attribution-sharealike license. Give it a read and then ask your questions in the chat. We can research this topic together.

This is an old revision of this page, as edited by 143.167.74.60 (talk) at 16:44, 16 July 2008 (Hofstadter vs Hinton). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Revision as of 16:44, 16 July 2008 by 143.167.74.60 (talk) (Hofstadter vs Hinton)(diff) ← Previous revision | Latest revision (diff) | Newer revision → (diff)

Hofstadter vs Hinton

I've edited this section to make it less confrontational and more factual. It's unlikely that either of them ripped off the idea from the other, and as there were conferences in 1984 called "the physics of cognitive processes" its probable that they were both reflecting general ideas from the community.

CRF

Is the Boltzmann machine the same as a Conditional Random Field? If so that should be mentioned somewhere!

No, it isn't. A CRF can however be viewed as convexified Boltzmann machine with hand-picked features. - DaveWF 06:10, 19 April 2007 (UTC)

The threshold

What is the importance of the threshold parameter? How is it set?

Learned like any other parameter. Just have a connection wired to '+1' all the time instead of another unit. I should add this. - DaveWF 06:10, 19 April 2007 (UTC)

Can threshold be referred to as bias? Also, the link on threshold takes you to the disambiguation page, which has no articles describing threshold in this context.

The Training Section

I have a problem understanding what is P+(Vα). P+ is the distribution of the states after the values for Vα are fixed. So P+(Vα) should be 1 for those fixed values and 0 for any other values to Vα.

Also, what does α iterate over in the summation for G?

The cost function

What is the cost function? What cost does it measure? How do we train the network if we have more than one input?

{-1,1} or {0,1} ?

In the definition of s the article claims that si is either -1 or 1. Five lines below, it says that the nodes are in state 0 or 1, which is also what I found in (admittedly older) literature on the subject. Is the {-1,1} simply wrong or am I missing something? — Preceding unsigned comment added by Drivehonor (talkcontribs) 13:56, 7 August 2007 (UTC)

I think either representation should work. But I'm not sure. Can anyone confirm this? —Preceding unsigned comment added by Zholyte (talkcontribs) 19:47, 10 November 2007 (UTC)