We present a system for computing similarity between pairs of words. Our system is based on Pair Hidden Markov Models, a variation on Hidden Markov Models that has been used successfully for the alignment of biological sequences. The parameters of the model are automatically learned from training data that consists of word pairs known to be similar. Our tests focus on the identification of cogn...

The author has recently proposed maximum-entropy hidden Markov models (MEHMMs) as an acoustic model for speech recognition [3]. Maximum-likelihood parameter estimation for MEHMMs poses a signi cant computational challenge, and so the experiments in that paper were arti cially limited by requiring • that the training data include the hidden state 1 sequence, and • that there be only a limited nu...

We describe and evaluate hidden understanding models, a statistical learning approach to natural language understanding. Given a string of words, hidden understanding models determine the most likely meaning for the string. We discuss 1) the problem of representing meaning in this framework, 2) the structure of the statistical model, 3) the process of training the model, and 4) the process of u...

An adaptive back-propagation algorithm is studied and compared with gradient descent (standard back-propagation) for on-line learning in two-layer neural networks with an arbitrary number of hidden units. Within a statistical mechanics framework , both numerical studies and a rigorous analysis show that the adaptive back-propagation method results in faster training by breaking the symmetry bet...

– A three-layered neural network that optimally self-adjusts the number of hidden layer units is proposed. The network combines two techniques : 1) Unit fusion which enables an efficient pruning of the redundant units. 2) Linear transformations applied to the chosen hidden layer unit pair output and a modified back-propagation training rule for gradual fusion to reduce pruning shocks. The netwo...

background: testosterone and its metabolites have important roles in learning and memory. the current study has conducted to assess the effect of pre-training, post-training and pre-probe trial intrahippocampal ca1 administration of 3 alpha-anderostanediol (one of the metabolites of testosterone) and indomethacin (as 3 alpha-hydroxysteroid dehydrogenase enzyme blocker) on acquisition, consolida...

Introduction: The possibility of depression is common in the elderly. Novel technologies allow us to monitor people related to depression. Hence, a model was provided to detect depression in elderly based on artificial neural network (ANN). Methods: The present study is an applied descriptive-survey research. Forty elderly people were randomly selected from the Elderly Care Center in Gonbad Ka...

Infiltration rate is one of the most important parameters used in irrigation water management. Direct measurement of infiltration process is laborious, time consuming and expensive. Therefore, in this study application of some indirect methods such as artificial neural networks (ANNs) for prediction of this phenomenon was investigated. Different ANNs structures including two training algorithms...