Although backpropagation ANNs generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions c...
Backpropagation, similar to most learning algorithms that can form complex decision surfaces, is prone to overfitting. This work presents classification-based objective functions, ...
Abstract--This paper presents a novel and domainindependent approach for graph-based structure learning. The approach is based on solving the Maximum Common SubgraphIsomorphism pro...
This paper presents a robust automatic shape classifier using modular wavelet networks (MWNs). A shape descriptor is constructed based on a combination of global geometric features...
Akshaya Kumar Mishra, Paul W. Fieguth, David A. Cl...
This paper presents an object categorization method. Our approach involves the following aspects of cognitive vision : machine learning and knowledge representation. A major eleme...