In this paper, a learning algorithm for a novel neural network architecture motivated by Integrate-and-Fire Neuron Model (IFN) is proposed and tested for various applications where a multilayer perceptron (MLP) neural network is conventionally used. It is observed that inclusion of a few more biological phenomenon in the formulation of artificial neural networks make them more prevailing. Several benchmark and real-life problems of classification and function-approximation are illustrated.
The Northern pine processionary moth, Thaumetopoea pinivora (Treitschke, 1834) shows a highly scattered distribution with fragmented populations across Europe. A previous study exploring the postglacial history of T. pinivora defined it as a cold-tolerant relict species and concluded that a progressive reduction of suitable habitats after the postglacial expansion from refugia in the southern Iberian peninsula best explained the distribution and genetic structure of populations of this species. However, recent records, both by us and others, challenge this view. Surprisingly, some of the newly found populations from southern Spain use black pine, Pinus nigra J.F. Arnold as a host plant despite the fact that the typical host of the species, Scots pine, Pinus sylvestris L. occurs in the area. We provide genetic data for one of these recently found southern populations where the larvae feed on P. nigra, and compare this with previously published data on individuals collected on P. sylvestris. This data reveals that populations from different host trees are no more genetically differentiated than populations sharing the same host plant. The findings of a wider diet breadth open the way to widen the search for the still unidentified glacial refugium of T. pinivora, and as such may contribute to a better understanding about how the species has spread across Europe., José A. Hódar, Anna Cassel-Lundhagen, Andrea Battisti, Stig Larsson., and Obsahuje bibliografii
In this paper, a local approach to the concept of g-entropy is presented. Applying the Choquet`s representation Theorem, the introduced concept is stated in terms of g-entropy.
In this paper we establish a new local convergence theorem for partial sums of arbitrary stochastic adapted sequences. As corollaries, we generalize some recently obtained results and prove a limit theorem for the entropy density of an arbitrary information source, which is an extension of case of nonhomogeneous Markov chains.