This paper presents a network architecture to interconnect mixed-signal VLSI1 integrate-and-fire neural networks in a way that the timing of the neural network data is preserved. ...
We designed subthreshold analog MOS circuits implementing an inhibitory network model that performs noise-shaping pulse-density modulation with noisy neural elements. Our aim is t...
Abstract. Compared to normal learning algorithms, for example backpropagation, the optimal bounded ellipsoid (OBE) algorithm has some better properties, such as faster convergence,...
A novel way to simulate Turing Machines (TMs) by Artificial Neural Networks (ANNs) is proposed. We claim that the proposed simulation is in agreement with the correct interpretatio...
This paper presents a dynamic neural filter for adaptive noise cancellation. The cancellation task is transformed to a system-identification problem, which is tackled by use of th...
Paris A. Mastorocostas, Dimitris N. Varsamis, Cons...