In the beginning of nineties, Hava Siegelmann proposed a new computational model, the Artificial Recurrent Neural Network (ARNN), and proved that it could perform hypercomputation....
Abstract. Intracellular recordings obtained under cutaneous and lemniscal stimulation show that the afferent fibers can establish excitatory and inhibitory synaptic connections w...
This paper is focused on determining the parameters of radial basis function neural networks (number of neurons, and their respective centers and radii) automatically. While this ...
: Thalamic neurons have an exclusive property named bursting response. Bursting response seems to have a critical role in producing saliency map and encoding conspicuity of locatio...
Abstract. It is generally accepted that some of the problems and ambiguities at the low level of processing can not be resolved without taking into account contextual expectations....
The space of bio-inspired hardware can be partitioned along three axes: phylogeny, ontogeny, and epigenesis. We refer to this as the POE model. Our Embryonics (for embryonic electr...
Complexity-penalization strategies are one way to decide on the most appropriate network size in order to address the trade-off between overfitted and underfitted models. In this p...
This work present the use of a neural structure to augment the quality of noisy images of liquid bridges to obtain a clear representation of its border in order to determine the ac...