Stochastic models such as mixture models, graphical models, Markov random fields and hidden Markov models have key role in probabilistic data analysis. In this paper, we have learned Gaussian mixture model to the pixels of an image. The parameters of the model have estimated by EM-algorithm.   In addition pixel labeling corresponded to each pixel of true image is made by Bayes rule. In fact, ...

This contribution proposes a decompositional iterative method for the steadystate analysis of Kronecker structured Markov chains [1]. The Markovian system, which is formed by a composition of subsystems using the Kronecker sum operator for local transitions and the Kronecker product operator for synchronized transitions, is assumed to have irreducible subsystem matrices associated with local tr...

This thesis investigates the efficient analysis, especially the model checking, of bounded stochastic Petri nets (SPNs) which can be augmented with reward structures. An SPN induces a continuous-time Markov chain (CTMC). A reward structure associates a reward to each state of the CTMC and defines a Markov reward model (MRM). The Continuous Stochastic Reward Logic (CSRL) permits to define sophis...

We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging since the learner interacts with the environment and possibly changes the fu...

We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging since the learner interacts with the environment and possibly changes the fu...

Decision-theoretic planning with risk-sensitive planning objectives is important for building autonomous agents or decision-support systems for real-world applications. However, this line of research has been largely ignored in the artificial intelligence and operations research communities since planning with risk-sensitive planning objectives is more complicated than planning with risk-neutra...

In the multi-sensor activity recognition domain, the input space is often large and contains irrelevant and overlapped features. It is important to perform feature selection in order to select the smallest number of features which can describe the outputs. This paper proposes a new feature selection algorithms using the maximal relevance and maximal complementary criteria (MRMC) based on neural...

Performance is a crucial factor in software system. For many software development groups, it remains easier to wait until a system has been built before evaluating its performance. Among the three most used techniques, measurement, simulation and analytic modeling , measurement is believed to be the most accurate method. But it is only feasible after system is implemented. Most organizations re...

This contribution is devoted to risk-sensitive and risk-neutral optimality in Markov decision chains. Since the traditional optimality criteria (e.g. discounted or average rewards) cannot reflect the variability-risk features of the problem, and using the mean variance selection rules that stem from the classical work of Markowitz present some technical difficulties, we are interested in expect...