This paper describes a silicon implementation of an Arti cial Neural Networks based on Coherent Pulse Width modulation techniques. Synapses use current generators controlled by an input Pulse Stream. Net charge generated is the product of synaptic current by pulse width. Neurons accumulate synaptic contributions and convert internal activation into an output Pulse Stream. A system optimized for...

Charged current (CC) and neutral current (NC) low energy neutrino cross section predictions from a variety of Monte Carlo generators in present use are compared against existing experimental data. Comparisons are made to experimental data on quasi-elastic, resonant and coherent single pion production, multiple pion production, single kaon production, and total inclusive cross sections, and are ...

We consider neural network models described by systems of (continuous time) differential equations. Th e dynamical nature of each model is identified, symmet ric networks being relat ed to gradient vector fields and asymmet ric networks decomposed into their gradient and Hamilt onian components . From thi s identification follows, in particular , a simple characterizat ion of st ructural stabil...

Set expansion aims to expand a small set of seed entities into complete relevant entities. Most existing approaches assume the input is unambiguous and completely ignore multi-faceted semantics As result, given {"Canon", "Sony", "Nikon"}, previous models return one mixed that are either Camera Brands or Japanese Companies. In this paper, we study task expansion, which capture all semantic facet...

Dynamic model reduction in power systems is necessary for improving computational efficiency. Traditional model reduction using linearized models or offline analysis would not be adequate to capture power system dynamic behaviors, especially the new mix of intermittent generation and intelligent consumption makes the power system more dynamic and non-linear. Realtime dynamic model reduction eme...

Dynamic model reduction in power systems is necessary for improving computational efficiency. Traditional model reduction using linearized models or offline analysis would not be adequate to capture power system dynamic behaviors, especially the new mix of intermittent generation and intelligent consumption makes the power system more dynamic and non-linear. Realtime dynamic model reduction eme...

We introduce a novel algorithm for factorial learning, motivated by segmentation problems in computational vision, in which the underlying factors correspond to clusters of highly correlated input features. The algorithm derives from a new kind of competitive clustering model, in which the cluster generators compete to explain each feature of the data set and cooperate to explain each input exa...

Flow in geophysical fluids is commonly summarized by coherent streams (e.g., conveyor belt flows in extratropical cyclones or jet streaks in the upper troposphere). Typically, parcel trajectories are calculated from the flow field and subjective thresholds are used to distinguish coherent streams of interest. This methodology contribution develops a more objective approach to distinguish cohere...

This paper presents an enhanced graph based parameter independent clustering technique. The algorithm produces highly coherent clusters in terms of visual representation and cluster validity measures. The technique finds highly coherent patterns of genes having high biological relevance. The method was tested on four real life datasets and the results compared with those of other similar algori...