The generalized delta rule (which is also known as error backpropagation) is a significant advance over previous procedures for network learning. In this paper, we compare network learning using the generalized delta rule to human learning on two concept identification tasks: • Relative ease of concept identification • Generalizing from incomplete data

The view of artificial neural networks as adaptive systems has lead to the development of ad-hoc generic procedures known as learning rules. The first of these is the Perceptron Rule (Rosenblatt, 1962), useful for single layer feed-forward networks and linearly separable problems. Its simplicity and beauty, and the existence of a convergence theorem made it a basic departure point in neural lea...

In arid and semi-arid environments, groundwater plays a significant role in the ecosystem. In the last decades, groundwater levels have decreased due to the increasing demand for water, weak irrigation management and soil damage. For the effective management of groundwater, it is important to model and predict fluctuations in groundwater levels. In this study, groundwater table in Kashan plain ...

Backpropagation learning algorithms typically collapse the network’s structure into a single vector of weight parameters to be optimized. We suggest that their performance may be improved by utilizing the structural information instead of discarding it, and introduce a framework for “tempering” each weight accordingly. In the tempering model, activation and error signals are treated as approxim...

This paper proposes a learning-based approach to synthesize cursive handwriting of the user’s personal handwriting style, by combining shape models and physical models together. In the training process, some sample paragraphs written by the user are collected and these cursive handwriting samples are segmented into individual characters by using a two-level writer-independent segmentation algor...

We introduce a learning algorithm for unsupervised neural networks based on ideas from statistical mechanics. The algorithm is derived from a mean eld approximation for large, layered sigmoid belief networks. We show how to (approximately) infer the statistics of these networks without resort to sampling. This is done by solving the mean eld equations, which relate the statistics of each unit t...

optimizing the database queries is one of hard research problems. exhaustive search techniques like dynamic programming is suitable for queries with a few relations, but by increasing the number of relations in query, much use of memory and processing is needed, and the use of these methods is not suitable, so we have to use random and evolutionary methods. the use of evolutionary methods, beca...

NeuroFAST is an on-line fuzzy modeling learning algorithm, featuring high function approximation accuracy and fast convergence. It is based on a first-order Takagi-Sugeno-Kang (TSK) model, where the consequence part of each fuzzy rule is a linear equation. Structure identification is performed by a fuzzy adaptive resonance theory (ART)-like mechanism, assisted by fuzzy rule splitting and adding...

Most shift operator-based adaptive algorithms exhibit poor numerical behavior when the input discrete time process is obtained from a continuous time process by fast sampling. This includes the shift operator based least squares lattice algorithm. In this paper, we develop a delta least squares lattice algorithm. This algorithm has low computational complexity compared to the delta Levinson RLS...

In this paper, An effective and simple numerical method is proposed for solving systems of integral equations using radial basis functions (RBFs). We present an algorithm based on interpolation by radial basis functions including multiquadratics (MQs), using Legendre-Gauss-Lobatto nodes and weights. Also a theorem is proved for convergence of the algorithm. Some numerical examples are presented...