1Department of Information Systems and Computer Science, National University of Singapore, Kent Ridge, Republic of Singapore.
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
This study introduces a novel penalty function for pruning feedforward neural networks, effectively reducing unnecessary connections and preventing large weights. The method achieved sparser networks on benchmark problems compared to existing techniques.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: