Current blind image quality prediction models rely on benchmark databases comprised of singly and synthetically distorted images, thereby learning image features that are only adequate to predict human perceived visual quality on such inauthentic distortions. However, real world images often contain complex mixtures of multiple distortions. Rather than a) discounting the effect of these mixture...

We present a technique for exact simulation of Gaussian Markov random fields (GMRFs), which can be interpreted as locally injecting noise to each Gaussian factor independently, followed by computing the mean/mode of the perturbed GMRF. Coupled with standard iterative techniques for the solution of symmetric positive definite systems, this yields a very efficient sampling algorithm with essentia...

In the last decade graphical models have become one of the most popular tools to structure uncertain knowledge about high-dimensional domains in order to make reasoning in such domains feasible. Their most prominent representatives are Bayesian networks and Markov networks, but also relational and possibilistic networks turned out to be useful in practical applications. For all types of network...

Deep belief networks (DBNs) have become a successful approach for acoustic modeling in speech recognition. DBNs exhibit strong approximation properties, improved performance, and are parameter efficient. In this work, we propose methods for applying DBNs to speaker recognition. In contrast to prior work, our approach to DBNs for speaker recognition starts at the acoustic modeling layer. We use ...

Recently, Deep Belief Networks (DBNs) have been proposed for phone recognition and were found to achieve highly competitive performance. In the original DBNs, only framelevel information was used for training DBN weights while it has been known for long that sequential or full-sequence information can be helpful in improving speech recognition accuracy. In this paper we investigate approaches t...

It is herein proposed a handwritten digit recognition system which biologically inspired of the large-scale structure of the mammalian neocortex. Hierarchical Temporal Memory (HTM) is a memory-prediction network model that takes advantage of the Bayesian belief propagation and revision techniques. In this article a study has been conducted to train a HTM network to recognize handwritten digits ...

One common principle in the study of belief is what has been called the “consensual validation of reality”: the idea that persons in highly inbred social networks alter their beliefs regarding the external world by repeated interaction with each other rather than by direct observation. This notion accounts for phenomena such as panics, in which a substantial number of actors in a given populati...

The common belief is that a Bayesian network may achieve better performance with a more complex structure than a simpler structure which usually sacrifice the power of knowledge representation. It is often thought that having some additional nodes than necessary for knowledge representation does not, at least, deteriorate the performance of a Bayesian network. In practice, people often add some...