Visual recognition faces the difficult problem of recognizing objects despite the multitude of their appearances. Ample neuroscientific evidence shows that the cortex uses a topogr...
In this paper we summarize our results for two classes of hierarchical multi-scale models that exploit contextual information for detection of structure in mammographic imagery. T...
Currently statistical and artificial neural network methods dominate in data mining applications. Alternative relational (symbolic) data mining methods have shown their effectivene...
The NIPS 2003 workshops included a feature selection competition organized by the authors. We provided participants with five datasets from different application domains and calle...
Isabelle Guyon, Steve R. Gunn, Asa Ben-Hur, Gideon...
The selection and control of action is a critical problem for both biological and machine animated systems that must operate in complex real world situations. Visually guided eye ...