The mitral cell primary dendrite plays an important role in transmitting distal olfactory nerve input from olfactory glomerulus to the soma-axon initial segment. To understand how dendritic active properties are involved in this transmission, we have combined dual soma and dendritic patch recordings with computational modeling to analyze action-potential initiation and propagation in the primar...

A new learning strategy is proposed for training of radial basis functions (RBF) network. We apply two different local optimization methods to update the output weights in training process, the gradient method and a combination of the gradient and Newton methods. Numerical results obtained in solving nonlinear integral equations show the excellent performance of the combined gradient method in ...

List of Symbols ej Measured strain wave at the position of the gauge j (j = a, b) e; e Positive and negative strain waves, respectively epj ; e n j Positive and negative strain waves at the position of the gauge j (j = a, b), respectively ei; er; et Incident, reflected and transmitted strain waves, respectively e ; epþ Positive strain waves at the front and back sides of rock joints, respective...

Neural networks offer an intriguing set of techniques for learning based on the ad-justment of weights of connections between processing units. However, the powerand limitations of connectionist methods for learning, such as the method of backpropagation in parallel distributed processing networks, are not yet entirely clear.We report on a set of experiments that more precisely ...

Computer worms have infected millions of computers since 1980s. For an incident handler or a forensic investigator, it is important to know whether the worm attack to the network has been initiated from multiple different sources or just from one node. In this paper, we study the problem of predicting the number of infectious nodes at each step of worm propagation, when the spread of a homogene...

-This paper presents a mathematical analysis of the occurrence of temporary minima during training of a single-output, two-layer neural network, with learning according to the back-propagation algorithm. A new vector decomposition method is introduced, which simplifies the mathematical analysis of learning of neural networks considerably. The analysis shows that temporary minima are inherent to...

Breast cancer diagnosis has been approached by various machine learning techniques for many years. This paper presents a study on classification of Breast cancer using Feed Forward Artificial Neural Networks. Back propagation algorithm is used to train this network. The performance of the network is evaluated using Wisconsin breast cancer data set for various training algorithms. The highest ac...

Algorithmic Differentiation (AD) provides the analytic derivatives of functions given as programs. Adjoint AD, which computes gradients, is similar to Back Propagation for Machine Learning. AD researchers study strategies to overcome the difficulties of adjoint AD, to get closer to its theoretical efficiency. To promote fruitful exchanges between Back Propagation and adjoint AD, we present thre...

In this paper, we describe a genetic algorithm (GA) based approach for learning connection weights for an artificial neural network (ANN). We use simulated data sets to compare the GA based approach for learning connection weights against the traditional back-propagation algorithm. Our results indicate that GA based training of ANN has a higher reliability (in terms of over-fitting the training...