Valerio Cimagalli

Optoelectronic cellular neural networks based on amorphous silicon thin film technology

In this paper, hardware realization of cellular neural networks in amorphous silicon thin film technology is proposed. In this way, it is possible to realize inexpensive large-scale, easily programmable circuits, with integrated light-sensing and light-emitting devices.<<ETX>>

Multifractal analysis of chaotic power spectra

Atistract. We analyse the scaling stmcture of power spectra arising from chaotic dynamical systems. The observation of anomalous scaling in spectral parameters can be understood by the use of multifractalanalysir in the frequencydomain.Thisanalysis provides numerical took for evaluating different chaotic behaviour. The frequency behaviour of oscillatory chaos seems to suggest the hypothesis of phase transition in the f (rr)-spenrum.

A dynamic approach to invariant extraction from time-varying inputs by using chaos in neural nets

The authors briefly summarize the main lines of the convergent and chaotic-bifurcative approaches in neural networks, and present a general model founded on an informational use of a chaotic dynamics. It exploits the inner fine structure of unstable periodic orbits of a chaotic dynamics to perform invariant extractions and reconstruction tasks in a dynamic way from a complex time-varying (at least chaotic) input. The neurophysiological background (i.e. synchronization behavior and functional segregation in the sensory cortex) is discussed. The proposed approach suggests that there exists a strict relationship in chaotic systems between dynamic reconstruction, optimization, and stabilization intended as a relaxation process in as much as they are all functions of an inner self-correlation process. This may depend on the fact that chaos, owing to its ultimate deterministic nature, is an intelligent noise. In the fine structure of its invariants, it retains a memory of its evolution

Short Term Evaluation of Brain Activities in fMRI Data by Spatiotemporal Independent Component Analysis

At present, Independent Components Analysis (ICA) represents the most important and efficient approach for extraction of independent non-Gaussian linearly mixed signals. This statistic-informative technique has been successfully applied to fMRI temporal data, which can be considered as an overlapped mixture of hemodynamic signals, physiological perturbations and noise. In this paper an extension to spatial application of ICA (sICA) was performed. The results confirmed that the spatial approach permits to obtain improved identification of brain activities, even when the temporal length of data is reduced.

A PROPOSAL TO IMPLEMENT OPTOELECTRONIC CNN SYSTEMS BY AMORPHOUS SILICON THIN FILM TECHNOLOGY

In this paper a hardware realization of cellular neural networks in amorphous silicon thin film technology is proposed. In this way, it is possible to realize inexpensive large-scale circuits. Integrated light-sensing and light-emitting devices make such systems complete image processing devices realized on a single substrate. Programmability can be achieved by means of luminous control signals.

Neural network reconstruction and prediction of chaotic dynamics

The work is devoted to the use of multilayer nonlinear perceptrons, trained with backpropagation, for reconstructing five known chaotic dynamics from their temporal series. In the case of finite-dimensional dynamics the authors tested the behavior of different structures and compared them with the results that can be obtained by using a quite different approach, i.e., functional reconstruction. The sigmoidal characteristic of neurons seems to lead to a better performance when dealing with a nonpolynomial dynamics. In the case of an infinite-dimensional dynamics the dependence of the prediction error on the size of the net and the delay parameter of the dynamics were investigated experimentally. Some hints for choosing network architecture and learning strategy are presented together with some suggestions for furthering such an investigation.<<ETX>>

Exact realization of large DT-CNNs on limited-sized CNN circuits

Since their introduction, Cellular Neural Networks have been constantly developed to include a broad class of problems. Despite their theoretical success, CNN implementations still suffer size limitations. In fact while the biggest CNN chips,due to VLSI constraints, have no more than few thousands of cells distributed on a 2D array, real problems may be multi-dimensional and may require millions of cells. In this paper we introduce a theoretical result allowing the emulation of a large DTCNN on a smaller and/or lower dimensional one. The smaller DTCNN will be equipped with some additional memory with respect to a standard DTCNN. Due to the theoretical formulation of the problem the DTCNN emulation has exactly the same behavior as the original one.

m-dimensional DT-CNN implementation via nested lower dimensional architecture

The development of the cellular neural network (CNN) paradigm, and its wide use in many application fields, has shown that CNN is a complementary, and in some cases alternative, approach to classical computing machines. Despite their theoretical success, CNN VLSI implementations still suffer from size and dimension limitations. In fact, while the biggest CNN chips, due to VLSI constraints and to planar technology, have no more than few thousands of cells arranged on a 2D array, real problems may require millions of cells and may be multidimensional. We focus on the implementation of an m-dimensional DT-CNN with a limited number of lower (m-i)-dimensional DT-CNN circuits. As the target dimension is (m-i), we choose i=m-2 or i=m-1. In order to obtain an architecture using 2D or ID DT-CNN circuits which were proven to be feasible.

Dynamic properties of an asymmetrical non-stationary neural net

Summary form only given, as follows. The authors have proposed a fully connected asymmetrical neural net with weight dynamics granting a continuous redefinition of its phase space. This is done by introducing two-site connectivities which are averages of two state products over a varying memory time tau . This system exhibits different behaviors (noiselike, chaotic, or stable) according to different values of its temporal control parameter. This is the ratio between the growth rate of tau and the velocity of the weight dynamics. In such a way, the probability distribution function of the states becomes nonstationary. Some hints were suggested to show how such a net is able to deal with second order statistics in particular for the recognition of moving objects in a noisy environment.<<ETX>>

Informational Versus Bifurcative Use of Chaotic Dynamics in Neural Networks

We discuss some basic problem in the mathematical theory of neural networks and suggest a new informational approach on the modeling of a chaotic architecture. Some example of this approach are given in connection to the building of coincidence detectors and 2D asymmetric spin glass systems that stabilize themselves in a non bifurcative way.