This paper deals with fuzzy cellular neural networks (FCNNs) with leakage delays and proportional delays. Applying the differential inequality strategy, fixed point theorem and almost periodic function principle, some sufficient criteria which ensure the existence and global attractivity of a unique almost periodic solution for fuzzy cellular neuralnetworks with leakage delays and p...

in this work quantitative structure activity relationship (qsar) methodology was applied for modeling and prediction of cellular response to polymers that have been designed for tissue engineering. after calculation and screening of molecular descriptors, linear and nonlinear models were developed by using multiple linear regressions (mlr) and artificial neural network (ann) methods. the root m...

Implanted brain electrodes construct the only means to electrically interface with individual neurons in vivo, but their recording efficacy and biocompatibility pose limitations on scientific and clinical applications. We showed that nanoelectronic thread (NET) electrodes with subcellular dimensions, ultraflexibility, and cellular surgical footprints form reliable, glial scar-free neural integr...

This paper deals with the advantages of so-called hybrid systems, that is, systems consisting of two or more different models. We present here two cellular automata coupled with artificial neural networks (neural CA). The first example is the model of a traffic regulating system. The cells of the CA represent different cars, and a certain neural net regulates the traffic. The second example sho...

This paper presents a sample of what evolved neural net circuit modules using the so called CoDi-1Bit neu-ral network model can do. The concern is to study the important issue of evolvability of the cellular automata (CA) based neural network circuits which grow and evolve in special FPGA (Field Programmable Gate Array) hardware. The specialized hardware which performs this evolution is labeled...

This work presents a sample of what evolved neural net circuit modules using the socalled "CoDi-1Bit" neural net model [5] can do. This work is part of an 8 year research project at ATR which aims to build an artificial brain containing a billion neurons by the year 2001, that will be used to control the behaviors of a kitten robot "Robokoneko" [2][3][4]. It looks as though the figure is more l...