We show how to use recursive function theory to prove Turing universality of finite analog recurrent neural nets, with a piecewise linear sigmoid function as activation function. W...
This paper presents a novel architecture for on-chip neural network training using particle swarm optimization (PSO). PSO is an evolutionary optimization algorithm with a growing ...
Amin Farmahini Farahani, Seid Mehdi Fakhraie, Saee...
Abstract. Current digital, directly mapped implementations of spiking neural networks use serial processing and parallel arithmetic. On a standard CPU, this might be the good choic...
Optical ow elds are a primary source of information about the visual scene in technical and biological systems. In a step towards a system for real time scene analysis we have deve...
Rainer A. Deutschmann, Charles M. Higgins, Christo...
Abstract: Reservoir Computing (RC) systems are powerful models for online computations on input sequences. They consist of a memoryless readout neuron which is trained on top of a ...