Related Experiment Videos

Data mining of inputs: analysing magnitude and functional measures

T D Gedeon1

  • 1Department of Information Engineering, School of Computer Science and Engineering, University of New South Wales, Sydney, Australia. tom@cse.unsw.edu.au

Summary

This study introduces new methods for feature selection in neural networks by analyzing weight matrices and functional input contributions. These techniques improve data encoding and identify significant inputs for better model training.

Related Concept Videos