rupen@csd4.csd.uwm.edu (Rupen Dinesh Sheth) (11/21/89)
I am new in the area of neural nets. I am trying to compare the neural net approach to the Bayesian Net approach (by Judea Pearl). Has anyone worked on this before? Is it true that single layer neural nets can perform similar to Bayesian belief networks, and if so has anyone done some theoretical work on it. Any pointers and/or suggested readings would be appreciated. ------------------------------------------------------------------------------ _ __ _ _ _ __ __ _ __ ' ) ) ' ) / ' ) ) / ` ' ) ) internet- rupen@csd4.csd.uwm.edu /--' / / /--' /-- / / bitnet- rupen%csd4.csd.uwm.edu@INTERBIT / \_ (__/ / (___, / (_ uucp- >internet:rupen@csd4.csd.uwm.edu
dhw@itivax.iti.org (David H. West) (11/21/89)
In article <1148@uwm.edu> rupen@csd4.csd.uwm.edu (Rupen Dinesh Sheth) writes: |I am new in the area of neural nets. I am trying to compare the neural net |approach to the Bayesian Net approach (by Judea Pearl). | |Has anyone worked on this before? Is it true that single layer neural nets |can perform similar to Bayesian belief networks, and if so has anyone done some |theoretical work on it. Typical 'neural net' neurons have an internal state that is characterised by a single scalar, and they perform a scalar calculation (on which some setups impose the complication of back-propagation, in which the links have a scalar state). Pearl's nodes must store a multi-dimensional matrix, and transmit vector messages over their links. -David West dhw@itivax.iti.org
hector@maui.cs.ucla.edu (Hector A Geffner) (11/23/89)
In article <4454@itivax.iti.org> dhw@itivax.UUCP (David H. West) writes: >In article <1148@uwm.edu> rupen@csd4.csd.uwm.edu (Rupen Dinesh Sheth) writes: >|I am new in the area of neural nets. I am trying to compare the neural net >|approach to the Bayesian Net approach (by Judea Pearl). >| >|Has anyone worked on this before? See "The Probabilistic Semantics of Connectionist Networks", by Geffner and Pearl, in the Proceedings of the First ICNN, San Diego, 1987, pp 187-195 >| .... Is it true that single layer neural nets >|can perform similar to Bayesian belief networks, and if so has anyone done >!some theoretical work on it. Not as far as i know. Representing Bayesian Networks in connectionist architectures requires in general higher order connections (eg w_{i,j,k,....}). >Typical 'neural net' neurons have an internal state that is >characterised by a single scalar, and they perform a scalar >calculation (on which some setups impose the complication of >back-propagation, in which the links have a scalar state). Pearl's >nodes must store a multi-dimensional matrix, and transmit vector >messages over their links. > >-David West dhw@itivax.iti.org For Bayesian Networks involving binary (two-valued) variables only, the vector messages can be reduced to scalars, and the matrix can be expressed in terms of weights and thresholds (see ref above). -hector
billchu@unccvax.UUCP (Tseng Bill Chu) (11/23/89)
Yun Peng and Jim Reggia has implemented several NN Baysian Belief nets. For detail please send mails to peng@cs.umd.edu or reggia@cs.umd.edu. Their scheme will result 99% correctness in finding the correct baysian hypothesis. --Bill