Learn More
  • Book Reviews, In Foreword, +7 authors G F Hudiakov
  • IEEE Transactions on Neural Networks
  • 2006
The reviewed book is devoted to the neural networks that are based on the neurons with the complex-valued weights and complex-valued activation functions. In recent years, these neural networks have becomemore andmore popular. A number of the original solutions in pattern recognition and classification, in artificial neural information processing, in image(More)
A fully adaptive normalized nonlinear gradient descent (FANNGD) algorithm for online adaptation of nonlinear neural filters is proposed. An adaptive stepsize that minimizes the instantaneous output error of the filter is derived using a linearization performed by a Taylor series expansion of the output error. For rigor, the remainder of the truncated Taylor(More)
A state-of-the-art integrated environment was created to study interaction among fire, structure and agent models in a fire evacuation from a typical office building. For the fire simulations NIST large-eddy simulation code Fire Dynamics Simulator (FDS) was used. The code is based on a mixture fraction model. FDS provided time resolved temperature, CO, CO2,(More)
A nonlinear gradient descent (NGD) learning algorithm with an adaptive amplitude of the nonlinearity is derived for the class of nonlinear finite impulse response (FIR) adaptive filters (dynamical perceptron). This is based on the adaptive amplitude backpropagation (AABP) algorithm for large-scale neural networks. The amplitude of the nonlinear activation(More)
Optimally designing radiotherapy and radiosurgery treatments to increase the likelihood of a successful recovery from cancer is an important application of operations research. Researchers have been hindered by the lack of academic software that supports head-to-head comparisons of different techniques, and this article addresses the inherent difficulties(More)
  • Book Reviews, In Foreword, +7 authors G F Hudiakov
  • 2006
The reviewed book is devoted to the neural networks that are based on the neurons with the complex-valued weights and complex-valued activation functions. In recent years, these neural networks have becomemore andmore popular. A number of the original solutions in pattern recognition and classification, in artificial neural information processing, in image(More)
  • 1