Limitations of one-hidden-layer (shallow) perceptron networks to sparsely represent multivariable functions is investigated. A concrete class of functions is described whose computation by shallow perceptron networks requires either large number of units or is unstable due to large output weights. The class is constructed using pseudo-noise sequences which have many features of random sequences...

an artificial neural network has been used to determine the volume flux and rejections of ca2+ , na+ and cl¯, as a function of transmembrane pressure and concentrations of ca2+, polyethyleneimine, and polyacrylic acid in water softening by nanofiltration process in presence of polyelectrolytes. the feed-forward multi-layer perceptron artificial neural network including an eight-neuron hidden la...

We present our experiments applying, off-the-shelf, two existing Named Entity Recognition (NER) taggers for the Biomedical Abbreviation Recognition and Resolution (BARR) task at IberEval 2017. The first system is a Perceptron tagger based on sparse, shallow features whereas the second is a bidirectional Long-Short Term Memory neural network with a sequential conditional random layer above it (L...

We examined closely the cerebellar circuit model that we have proposed previously. The model granular layer generates a finite but very long sequence of active neuron populations without recurrence, which is able to represent the passage of time. For all the possible binary patterns fed into mossy fibres, the circuit generates the same number of different sequences of active neuron populations....

For the past decades, computational fluid dynamics (CFD) simulations have been shown as a promising approach for understanding complex flow behavior of concrete. However, their application is often limited due to computationally heavy analysis. In this study, two artificial neural networks, multi-layer perceptron and radial basis function, are trained by results CFD model that simulates cement ...

A classic problem in neural networks is the depth investigation of the network. Is there any potential benefit when training depth-one threshold circuits by adding extra layers and further training them? This question is investigated in a powerful recently introduced artificial intelligence system, called the Logarithmic Simulated Annealing (LSA) machine, that combines the Simulated Annealing A...

<span lang="EN-US">Recently, navigation in an unknown environment without hitting obstacles was considered a big challenge faced by researchers. The difficulty finding good mathematical model for the different systems is deciding to use artificial intelligent controllers control mobile robot movement. In this paper, designing two multi-layer-perceptron neural networks (MLP-NN) done moveme...