The prediction of the ultimate bearing capacity of the pile under axial load is one of the important issues for many researches in the field of geotechnical engineering. In recent years, the use of computational intelligence techniques such as different methods of artificial neural network has been developed in terms of physical and numerical modeling aspects. In this study, a database of 100 p...

land cover map is important for many urban planning and management activities. in this study, in order to produce land cover map of arak city, digital image of liss-iii scanner acquired on 16 june 2006 were employed. first of all, geometric correction with rmse 0.58 pixel was applied. considering the mountainous condition of the study area, topographic correction was applied to the image. in su...

Neural networks are split into 2 main categories; namely supervised & unsupervised In supervised learning the neural network is pravided with the desired response for a particular example. The unsupervised neural network does not require the desired response but determines itself what properties exist and learns to reflect these properties in its output. This has successfully been used for segm...

In this paper, we show that noise injection into inputs in unsupervised learning neural networks does not improve their performance as it does in supervised learning neural networks. Specifically, we show that training noise degrades the classification ability of a sparsely connected version of the Hopfield neural network, whereas the performance of a sparsely connected winner-take-all neural n...

‡ Supervised learning. Introduced the idea of a “cost” function over weight space Regression and learning in linear neural networks. The cost was the sum of squared differences between the networks predictions of the correct answers and the correct answers. The motivation was to derive a “learning rule” that adjusts (synaptic) weights to minimize the discrepancy between predictions and answers....

Most Artificial Neural Networks (ANNs) have a fixed topology during learning, and typically suffer from a number of short-comings as a result. Variations of ANNs that use dynamic topologies have shown ability to overcome many of these problems. This paper introduces Location-Independent Transformations (LITs) as a general strategy for parallel implementation of feedforward networks that use dyn...