Title :
A hybrid Bayesian neural learning strategy applied to CONNECT-4
Author :
Abdelbar, Ashraf M. ; Tagliarini, Gene A.
Author_Institution :
Dept. of Comput. Sci., American Univ. in Cairo, Egypt
Abstract :
We present a method that combines Bayesian learning, a statistical technique, with the HONEST network, a high order neural network with the property that the mapping embodied by the network can always be described by a polynomial-like equation. In a classification task, the objective is to learn to classify feature vectors into classes. When the distribution of the features is known, statistical methods can often produce better performance than backward error propagation networks. However, if the feature distribution is not known for certain, then the performance of a statistical method will depend on how well the assumed distribution matches the actual distribution. In the method we present, we first use Bayesian learning, with an assumption of a multivariate normal distribution, to learn a quadratic polynomial mapping and then use the HONEST network to improve, or fine-tune, this mapping through backward error propagation. We apply this technique to the feature combination stage of a CONNECT-4 evaluation function
Keywords :
Bayes methods; backpropagation; games of skill; neural nets; normal distribution; pattern classification; CONNECT-4 evaluation function; HONEST network; backward error propagation; classification task; feature combination; feature vectors; high order neural network; hybrid Bayesian neural learning strategy; multivariate normal distribution; polynomial-like equation; quadratic polynomial mapping; statistical technique; Bayesian methods; Computer errors; Computer science; Databases; Equations; Gaussian distribution; Neural networks; Pattern recognition; Polynomials; Statistical analysis;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.682300