Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
2001-02-23
Physics
Condensed Matter
Disordered Systems and Neural Networks
22 pages, 5 figures, submitted to Neural Computation, v2. significant structural changes
Scientific paper
We continue to explore the hypothesis that neuronal populations represent and process analog variables in terms of probability density functions (PDFs). A neural assembly encoding the joint probability density over relevant analog variables can in principle answer any meaningful question about these variables by implementing the Bayesian rules of inference. Aided by an intermediate representation of the probability density based on orthogonal functions spanning an underlying low-dimensional function space, we show how neural circuits may be generated from Bayesian belief networks. The ideas and the formalism of this PDF approach are illustrated and tested with several elementary examples, and in particular through a problem in which model-driven top-down information flow influences the processing of bottom-up sensory input.
Anderson Charles H.
Barber Michael J.
Clark John Willis
No associations
LandOfFree
Neural Propagation of Beliefs does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Neural Propagation of Beliefs, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural Propagation of Beliefs will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-465589