Titlebook: Neural Nets; 16th Italian Worksho Bruno Apolloni,Maria Marinaro,Roberto Tagliaferri Conference proceedings 2006 Springer-Verlag Berlin Heid

編輯才信任

Recursive Neural Networks and Graphs: Dealing with Cycles this paper, the methodology proposed in [1,2] to process cyclic directed graphs is tested on some interesting problems in the field of structural pattern recognition. Such preliminary experimentation shows very promising results.

vanquish

A System for Transmitting a Coherent Burst of Activity Through a Network of Spiking Neuronsl with the coherence of spike trains and show that it is possible for a burst of spikes emitted by a layer to not diverge when passing through different layers of neurons. We present the results of simulations done on a multi layered feed-forward system to illustrate our method.

Commission

Hourly Forecasting of SO2 Pollutant Concentration Using an Elman Neural Networkind velocity, the wind direction, the stability classes of Thomas, the base level of the layer of the atmospheric stability, the gradient of the potential temperature and the difference of the potential temperature of reference.

描述

bronchodilator

琺瑯

A New Neural Network Model for Contextual Processing of Graphsloits the contextual information stored in the hidden units progressively added to the network, without introducing cycles in the definition of the state variables. In contrast to previous neural networks for structures, NN4G is not recursive but uses standard neurons (with no feedbacks) that traver

無法解釋

Approximation Properties of Positive Boolean Functionsf approximating within a desired precision any Borel measurable function guarantees the generality of the considered approach..The properties of the class of positive Boolean functions, realizable by digital circuits containing only . and . ports, is examined by considering a proper coding for order

的事物

scoliosis

Ensembles Based on Random Projections to Improve the Accuracy of Clustering Algorithmsensionality reduction is obtained. Multiple clusterings are performed on random subspaces, approximately preserving the distances between the projected data, and then they are combined using a pairwise similarity matrix; in this way the accuracy of each “base” clustering is maintained, and the diver

BOAST