We propose a multimodal retrieval procedure based on latent feature models. The procedure consists of a Bayesian nonparametric framework for learning underlying semantically meaningful abstract features in a multimodal dataset, a probabilistic retrieval model that allows cross-modal queries and an extension model for relevance feedback. Experiments on two multimodal datasets, PASCAL-Sentence an...

Reinforcement learning has been active research area not only in machine learning but also in control engineering, operation research and robotics in recent years. It is a model free learning control method that can solve Markov decision problems. Q-learning is an incremental dynamic programming procedure that determines the optimal policy in a step-by-step manner. It is an online procedure for...

Learning is a flexible and effective means of extracting the stochastic structure of the environment. It provides an effective method for blind separation and deconvolution in signal processing. Two different types of learning are used, namely batch learning and on-line learning. The batch learning procedure uses all the training examples repeatedly so that its performance is compared to the st...

A learning test procedure based on operant principles may be useful in the diagnosis (and eventually rehabilitation) of post-coma persons with minimal responsiveness. This study was aimed at extending the evaluation of such a procedure with seven participants who presented with very limited behavior and apparently severe disorders of consciousness. The procedure was evaluated through an ABACB d...

Cognitive procedural learning occurs in three qualitatively different phases (cognitive, associative, and autonomous). At the beginning of this process, numerous cognitive functions are involved, subtended by distinct brain structures such as the prefrontal and parietal cortex and the cerebellum. As the learning progresses, these cognitive components are gradually replaced by psychomotor abilit...

We have developed a discourse level tagging tool for spoken dialogue corpus using machine learning methods. As discourse level information, we focused on dialogue act, relevance and discourse segment. In dialogue act tagging, we have implemented a transformation-based learning procedure and resulted in 70% accuracy in open test. In relevance and discourse segment tagging, we have implemented a ...

introduction. this is quasi experimental research in order to determine and compare the learning level of nursing skills ( in b.a students) with self-directed learning and tutor-directed learning pattern in shaheed beheshti univeristy of medical sciences and health services, nursing and midwifery faculty, 1998-1999. methods. first of all, a questionnaire composed of some demographic data such a...