Sciweavers

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

13

ISCI
1998

favoriteEmaildiscussreport

83views more ISCI 1998»

On Generalization by Neural Networks

13 years 4 months ago

On Generalization by Neural Networks

Download www.ece.lsu.edu

We report new results on the corner classiﬁcation approach to training feedforward neural networks. It is shown that a prescriptive learning procedure where the weights are simply read oﬀ based on the training data can provide good generalization. The paper also deals with the relations between the number of separable regions and the size of the training set for a binary data network. Prescriptive learning can be particularly valuable for real-time applications.

Subhash C. Kak

Real-time Traffic

Corner Classiﬁcation Approach | Feedforward Neural Networks | ISCI 1998 | Prescriptive Learning Procedure |

claim paper

Related Content

» The Cellular Simultaneous Recurrent Network Adaptive Critic Design for the Generalized Maz...

» General Transient Length Upper Bound for Recurrent Neural Networks

» Improving the Generalization Capability of the Binary CMAC

» Highly Modular Architecture for the General Control of Autonomous Robots

» Continuous Neural Decoding Method Based on General Regression Neural Network

» Toyota Prius HEV neurocontrol

» A Fast FPGA Implementation of a General Purpose Neuron

» Short Term Memories and Forcing the Reuse of Knowledge for Generalization

» Comparing Performance of Neural Networks Applied to a Simplified Recognition Problem

» Adaptive Wavelet Neural Network for Prediction of Hourly NOx and NO2 Concentrations

Post Info
More Details (n/a)

Added	22 Dec 2010
Updated	22 Dec 2010
Type	Journal
Year	1998
Where	ISCI
Authors	Subhash C. Kak

Comments (0)