In this paper, we study the problem of optimizing a two-layer artificial neural network that best fits a training dataset. We look at this problem in the setting where the number of parameters is greater than the number of sampled points. We show that for a wide class of differentiable activation functions (this class involves “almost” all functions which are not piecewise linear), we have that...

In this paper, we propose a hybrid learning algorithm for the single hidden layer feedforward neural networks (SLFNs) for data classification. The proposed hybrid algorithm is a two-phase learning algorithm and is based on the quasisecant and the simulated annealing methods. First, the weights between the hidden layer and the output layer nodes (output layer weights) are adjusted by the quasise...

pomegranate is an important iranian-native fruit, with many varieties cultivated. although the volume of data on the importance of pomegranates in human nutrition has increased tremendously in the last years, the physical properties of the pomegranate fruit during fruit maturity have not yet been studied in detail. thus, the present study aimed to evaluate changes in physical characteristics of...

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...

Modelling is carried out to map the relationship between the input process parameters and the output response, considered in the machining process. To represent real-world systems of considerable complexity, an artificial neural network (ANN) model is often utilized to replace the mathematical approximation of the relationship. This paper explains the methodological procedure and the outcome of...

A fundamental aspect of limitations in learning any computation in neural architectures is characterizing their optimal capacities. An important, widely-used neural architecture is known as autoencoders where the network reconstructs the input at the output layer via a representation at a hidden layer. Even though capacities of several neural architectures have been addressed using statistical ...

Neuro-fuzzy modeling has been intensively studied since the early nineties. Recently a method has been disclosed, that uses a classical feedforward neural network with just one hidden layer. Nodes of the hidden layer use the logistic function as activation function meanwhile the output node has a linear activation function. This paper introduces a generalization of the logistic function and eva...

The results of a recent study have provided direct support for the suggestion that conditional learning in rats is best characterized by a 3-layer connectionist network (M. J. Allman, J. Ward-Robinson, & R. C. Honey, 2004). In the 2 experiments reported here, rats were used to investigate the nature of the changes that occur when a stimulus compound is presented, whose components activate hidde...

Many interesting human actions involve multiple interacting agents and also have typical durations. Further, there is an inherent hierarchical organization of these activities. In order to model these we introduce a new family of hidden Markov models (HMMs) that provide compositional state representations in both space and time and also a recursive hierarchical structure for inference at higher...