Adapting connectionist learning to Bayes networks
نویسندگان
چکیده
منابع مشابه
Complex learning in connectionist networks
n Corresponding author at: IT4 Innovations, Center for Excellence, VSB-Technical neural network (connectionist network) design. In the literature, a number of such learning methods are available and are broadly classified as supervised, unsupervised and reinforcement learning. This special issue introduces novel complex learning procedures for handling different types of data in several applica...
متن کاملConnectionist Learning of Belief Networks
Neal, R.M., Connectionist learning of belief networks, Artificial Intelligence 56 (1992) 71-113. Connectionist learning procedures are presented for "sigmoid" and "noisy-OR" varieties of probabilistic belief networks. These networks have previously been seen primarily as a means of representing knowledge derived from experts. Here it is shown that the "Gibbs sampling" simulation procedure for s...
متن کاملLearning Optimal Augmented Bayes Networks
Naive Bayes is a simple Bayesian classifier with strong independence assumptions among the attributes. This classifier, despite its strong independence assumptions, often performs well in practice. It is believed that relaxing the independence assumptions of a naive Bayes classifier may improve the classification accuracy of the resulting structure. While finding an optimal unconstrained Bayesi...
متن کاملBilingual Language Learning in Connectionist Networks
Introduction Connectionist modeling opens up a venue to research on language learning from the statistical point of view. Network input construction offers a way to examine what kind of knowledge could be statistically learned and internal representations from network hidden units help to clarify how the knowledge thereafter could be represented in human minds (Elman, 1991; St. John & McClellan...
متن کاملLearning Phonetic Features Using Connectionist Networks
A method for learning phonetic features from speech data using connectionist networks is described. A temporal flow model is introduced in which sampled speech data flows through a parallel network from input to output units. The network uses hidden units with recurrent links to capture spectral/temporal characteristics of phonetic features. A supervised learning algorithm is presented which pe...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: International Journal of Approximate Reasoning
سال: 1990
ISSN: 0888-613X
DOI: 10.1016/0888-613x(90)90002-j