We propose a new way of embedding shape distributions in a topological deformable template. These distributions rely on global shape descriptors corresponding to the 3D moment inva...
Abstract-In this paper, we construct a neural-inspired computational model based on the representational capabilities of receptive fields. The proposed model, known as Shape Encodi...
Clio is a joint research project between the University of Toronto and IBM Almaden Research Center started in 1999 to address both foundational and systems issues related to the ma...
Learning how to create, test, and revise models is a central skill in scientific reasoning. We argue that qualitative modeling provides an appropriate level of representation for ...
Kenneth D. Forbus, Karen Carney, Bruce L. Sherin, ...
Machine learning with few training examples always leads to over-fitting problems, whereas human individuals are often able to recognize difficult object categories from only one ...