Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

14

ISCI
2002

favoriteEmaildiscussreport

120views more ISCI 2002»

A class of instantaneously trained neural networks

13 years 4 months ago

A class of instantaneously trained neural networks

Download www.ece.lsu.edu

This paper presents FC networks that are instantaneously trained neural networks that allow rapid learning of non-binary data. These networks, which generalize the earlier CC networks, have been compared against Backpropagation (BP) and Radial Basis Function (RBF) networks and are seen to have excellent performance for prediction of time-series and pattern recognition. The networks can generalize using soft or hard decisions.

Subhash C. Kak

Real-time Traffic

Earlier Cc Networks | FC Networks | ISCI 2002 | Neural Networks |

claim paper

Related Content

» Partial Discriminative Training of Neural Networks for Classification of Overlapping Class...

» Variable projections neural network training

» Identification of finite state automata with a class of recurrent neural networks

» Towards the Optimal Learning Rate for Backpropagation

» A New Wavelet Back Propagation Neural Networks for Structural Dynamic Analysis

» Training Feedforward Neural Networks Using Genetic Algorithms

» A cloning approach to classifier training

» Novel maximummargin training algorithms for supervised neural networks

» Combining Neural Networks Based on DempsterShafer Theory for Classifying Data with Imperfe...

Post Info
More Details (n/a)

Added	22 Dec 2010
Updated	22 Dec 2010
Type	Journal
Year	2002
Where	ISCI
Authors	Subhash C. Kak

Comments (0)