Automatic Generation of Initial Weights and Estimation of Hidden Units for Pattern Classi cation Using Neural Networks

Automatic generation of initial weights and estimation of hidden units for pattern classification using neural networks

Constructive training of probabilistic neural networks

This paper presents an easy to use constructive training algorithm for Probabilis tic Neural Networks a special type of Radial Basis Function Networks In contrast to other algorithms prede nition of the network topology is not required The pro posed algorithm introduces new hidden units whenever necessary and adjusts the shape of already existing units individually to minimize the risk of miscl...

Comparison of artificial neural network and multivariate regression methods in prediction of soil cation exchange capacity (Case study: Ziaran region)

Investigation of soil properties like Cation Exchange Capacity (CEC) plays important roles in study of environmental reaserches as the spatial and temporal variability of this property have been led to development of indirect methods in estimation of this soil characteristic. Pedotransfer functions (PTFs) provide an alternative by estimating soil parameters from more readily available soil data...

Rule-Extraction from Radial Basis Function Networks

Radial basis neural (RBF) networks provide an excellent solution to many pattern recognition and classi cation problems. However, RBF networks are also a local representation technique that enables the easy conversion of the hidden units into symbolic rules. This paper examines rules extracted from RBF networks. We use the iris ower classication task and a vibration diagnosis classi cation task...

DistAl: An inter-pattern distance-based constructive learning algorithm

Multi-layer networks of threshold logic units o er an attractive framework for the design of pattern classi cation systems. A new constructive neural network learning algorithm (DistAl) based on inter-pattern distance is introduced. DistAl uses spherical threshold neurons in a hidden layer to nd a cluster of patterns to be covered (or classi ed) by each hidden neuron. It does not depend on an i...