Deep latent variable models are powerful tools for representation learning. In this paper, we adopt the deep information bottleneck model, identify its shortcomings and propose a model that circumvents them. To this end, we apply a copula transformation which, by restoring the invariance properties of the information bottleneck method, leads to disentanglement of the features in the latent spac...

A spiking neural network (SNN) model trained with spiking-timingdependent-plasticity (STDP) is proposed to perform a 2D co-ordinate transformation of the polar representation of an arm position to a Cartesian representation in order to create a virtual image map of a haptic input. The position of the haptic input is used to train the SNN using STDP such that after learning the SNN can perform t...

of the Dissertation Comprehensive Memory Error Protection via Diversity and Taint-Tracking by Lorenzo Cavallaro Doctor of Philosophy in Computer Science Università degli Studi di Milano 2007 Memory errors in C and C++ programs are one of the oldest classes of vulnerabilities. Attackers have been exploiting these errors since late 80’s and these issues are still a real and concrete threat. To da...

BACKGROUND The purpose of this work is to provide experimental evidence on the interactions of suspended nanoparticles with artificial or biological membranes and to assess the possibility of suspended nanoparticles interacting with the lipid component of biological membranes. METHODS 1-Palmitoyl-2-oleoyl-sn-glycero-3-phosphocholine (POPC) lipid vesicles and human red blood cells were incubat...

When using the human mind as a template for artificial intelligence systems, principles of human thinking have to be modeled. One such very important principle is defense. Hence, in this article we describe a formalism to implement psychoanalytic defense mechanisms in artificial intelligence systems. They can be seen as transformations. A tuple consisting of perceptions or drives (of a software...

The paper proposes the idea of the error correction algorithm for the fractal dimension estimation based on the linear transformation approach allowing the estimation accuracy to be improved essentially. The proposed algorithm is based on the use of the isarithm and triangular prism estimation methods. The results of comparison of a few fractal dimension estimation methods with the use of artif...

A technique is proposed for the adaptation of automatic speech recognition systems using Hybrid models combining Artificial Neural Networks with Hidden Markov Models. We investigated in this paper the extension of the classical approach consisting in applying linear transformations not only to the input features, but also to the outputs of the internal layers. The motivation is that the outputs...

This paper presents our research in image processing (filters used for edges detection, color transformation, and distortion correction) using Artificial Neural Networks. We have developed a tool, Neuron Color, in order to do this kind of experiments and improving our adaptive methods.

Geocentric translation model (GTM) in recent times has not gained much popularity in coordinate transformation research due to its attainable accuracy. Accurate transformation of coordinate is a major goal and essential procedure for the solution of a number of important geodetic problems. Therefore, motivated by the successful application of Artificial Intelligence techniques in geodesy, this ...

bainitic transformation at low transformation temperatures leads to a microstructure involving fine plates of bainitic ferrite and thin films of retained austenite. this microstructure has shown ultimate tensile strength of about 2.2 gpa, noticeable uniform elongation in the range of 5 to 30%, hardness values of about 600 to 670 hv and impact toughness in the range of 30 to 40 mpa m1/2. with ca...