Evaluating functional autocorrelation within spatially distributed neural processing networks

Spatially distributed cellular neural networks

Purpose – The objective of this work is to develop a methodology for the design of cellular neural networks with interconnection topologies optimized and suitable for spatially distributed implementation. Design/Methodology/Approach – We perform combinatorial optimization on the neural network’s topology to obtain a sparser network, in which the links between the components of the network that ...

Spatially distributed social complex networks

We propose a bare-bones stochastic model that takes into account both the geographical distribution of people within a country and their complex network of connections. The model, which is designed to give rise to a scale-free network of social connections and to visually resemble the geographical spread seen in satellite pictures of the Earth at night, gives rise to a power-law distribution fo...

Spatially-sparse convolutional neural networks

Convolutional neural networks (CNNs) perform well on problems such as handwriting recognition and image classification. However, the performance of the networks is often limited by budget and time constraints, particularly when trying to train deep networks. Motivated by the problem of online handwriting recognition, we developed a CNN for processing spatially-sparse inputs; a character drawn w...

Modularity within Neural Networks

Distributed Approximating Functional Networks

We present a novel polynomial functional neural networks using Distributed Approximating Functional (DAF) wavelets (infinitely smooth filters in both time and frequency regimes), for signal estimation and surface fitting. The remarkable advantage of these polynomial nets is that the functional space smoothness is identical to the state space smoothness (consisting of the weighting vectors). The...