We present a new type of probabilistic model which we call DISsimilarity COefficient Networks (DISCO Nets). DISCO Nets allow us to efficiently sample from a posterior distribution parametrised by a neural network. During training, DISCO Nets are learned by minimising the dissimilarity coefficient between the true distribution and the estimated distribution. This allows us to tailor the training...

Simultaneous localization and mapping (SLAM) system typically employs vision-based sensors to observe the surrounding environment. However, performance of such systems highly depends on ambient illumination conditions. In scenarios with adverse visibility or in presence airborne particulates (e.g., smoke, dust, etc.), alternative modalities as those based thermal imaging inertial are more promi...

Abstract--In this study, we introduce a concept of self-organizing neurofuzzy networks (SONFN), a hybrid modeling architecture combining relation-based neurofuzzy networks (NFN) and self-organizing polynomial neural networks (PNN). For such networks we develop a comprehensive design methodology and carry out a series of numeric experiments using data coming from the area of software engineering...

In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for deterministic neural networks and supervised tasks, ZhuSuan is featured for its deep root into Bayesia...

We present a new type of probabilistic model which we call DISsimilarity COefficient Networks (DISCO Nets). DISCO Nets allow us to efficiently sample from a posterior distribution parametrised by a neural network. During training, DISCO Nets are learned by minimising the dissimilarity coefficient between the true distribution and the estimated distribution. This allows us to tailor the training...

* This work was partially supported by the Italian MURST. AbstractThe aim of this paper is to present a novel technique for defect identification by neural networks based on the classification of remote field effect eddy current (RFEC) data. We consider a kind of neural network that does not require a long training and is particularly well suited for fast classification, the Probabilistic Neura...

Probabilistic modeling enables combining domain knowledge with learning from data, thereby supporting learning from fewer training instances than purely data-driven methods. However, learning probabilistic models is difficult and has not achieved the level of performance of methods such as deep neural networks on many tasks. In this paper, we attempt to address this issue by presenting a method...

In this paper, a probabilistic neural network (PNN) based classifier is used to judge the static security of the power system. The proposed classifier classifies the security of the power system based on the voltage profile of each bus in reference to changes in the generation and load profile in the system. The probabilistic neural network is used and compared with the radial basis function ne...