Results 231 to 240 of about 27,765 (261)

Channel equalization by feedforward neural networks

ISCAS'99. Proceedings of the 1999 IEEE International Symposium on Circuits and Systems VLSI (Cat. No.99CH36349), 2003
A signal suffers from nonlinear, linear, and additive distortion when transmitted through a channel. Linear equalizers are commonly used in receivers to compensate for linear channel distortion. As an alternative, nonlinear equalizers have the potential to compensate for all three sources of channel distortion.
Biao Lu, Brian L. Evans
openaire   +1 more source

Feedforward Neural Networks and Training Methods

2007
10.1007/978-3-540-69226-3_2 ; Studies in Computational Intelligence ; 53 ; 9 ...
Tang H., Tan K.C., Yi Z.
openaire   +3 more sources

Visualizing the Function Computed by a Feedforward Neural Network

Neural Computation, 2000
A method for visualizing the function computed by a feedforward neural network is presented. It is most suitable for models with continuous inputs and a small number of outputs, where the output function is reasonably smooth, as in regression and probabilistic classification tasks. The visualization makes readily apparent the effects of each input and
Tony Plate, Pierre Band, Joel Bert, John Grace   +3 more
openaire   +3 more sources

Feedforward Neural Network Methodology

IEEE Transactions on Neural Networks, 2001
Ke Chen 0001, V. Kvasnicka, P. C. Kanen, Simon Haykin 0001   +3 more
openaire   +2 more sources

Feedforward Neural Networks

2022
Ashwin Pajankar, Aditya Joshi
openaire   +2 more sources

ACCELERATING TRAINING OF FEEDFORWARD NEURAL NETWORKS

International Journal on Artificial Intelligence Tools, 1994
We review methods and techniques for training feedforward neural networks that avoid problematic behavior, accelerate the convergence, and verify the training. Adaptive step gain, bipolar activation functions, and conjugate gradients are powerful stabilizers.
openaire   +2 more sources

A multinomial characterization of feedforward neural networks

Proceedings of 1995 Conference on Computational Intelligence for Financial Engineering (CIFEr), 2002
The purpose of the paper is to examine neural networks in terms of a particular probability model: a multinomial distribution characterization of the conditional mean. This characterization suggests circumstances in which networks need only provide good local approximations and a new parsimonious neural network model.
openaire   +1 more source

Feedforward Neural Network Methodology

Technometrics, 2000
openaire   +2 more sources

Transformational theory of feedforward neural networks

Neural Networks, 1988
David A. Cohen, C. Mannion, John Shawe-Taylor   +2 more
openaire   +2 more sources

Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results

Neural Networks, 1998
Franco Scarselli, Ah Chung Tsoi
exaly