Global Boltzmann perceptron network for online learning of conditional distributions
| Autor: | M.T. Arvind, M.A.L. Thathachar |
|---|---|
| Rok vydání: | 1999 |
| Předmět: |
Mathematical optimization
Weak convergence Artificial neural network Computer Networks and Communications General Medicine Conditional probability distribution Perceptron Iris flower data set Backpropagation Computer Science Applications Artificial Intelligence Feedforward neural network Probability distribution Algorithm Software Mathematics |
| Zdroj: | IEEE Transactions on Neural Networks. 10:1090-1098 |
| ISSN: | 1045-9227 |
| DOI: | 10.1109/72.788649 |
| Popis: | This paper proposes a backpropagation-based feedforward neural network for learning probability distributions of outputs conditioned on inputs using incoming input-output samples only. The backpropagation procedure is shown to locally minimize the Kullback-Leibler measure in an expected sense. The procedure is enhanced to facilitate boundedness of weights and exploration of the search space to reach a global minimum. The weak convergence theory is employed to show that the long-term behavior of the resulting algorithm can be approximated by that of a stochastic differential equation, whose invariant distributions are concentrated around the global minima of the Kullback-Leibler measure within a region of interest. Simulation studies on problems involving samples arriving from a mixture of labeled densities and the well-known Iris data problem demonstrate the speed and accuracy of the proposed procedure. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|