Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
1998-08-04
Physics
Condensed Matter
Disordered Systems and Neural Networks
88 pages, 9 figures (enlarged version)
Scientific paper
A new general framework is presented for implementing complex a priori knowledge, having in mind especially situations where the number of available training data is small compared to the complexity of the learning task. A priori information is hereby decomposed into simple components represented by quadratic building blocks (quadratic concepts) which are then combined by conjunctions and disjunctions to built more complex, problem specific error functionals. While conjunction of quadratic concepts leads to classical quadratic regularization functionals, disjunctions, representing ambiguous priors, result in non--convex error functionals. These go beyond classical quadratic regularization approaches and correspond, in Bayesian interpretation, to non--gaussian processes. Numerical examples show that the resulting stationarity equations, despite being in general nonlinear, inhomogeneous (integro--)differential equations, are not necessarily difficult to solve. Appendix A relates the formalism of statistical mechanics to statistics and Appendix B describes the framework of Bayesian decision theory.
No associations
LandOfFree
How to Implement A Priori Information: A Statistical Mechanics Approach 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 How to Implement A Priori Information: A Statistical Mechanics Approach, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and How to Implement A Priori Information: A Statistical Mechanics Approach will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-393861