A significant problem for evolving artificial neural networks is that the physical arrangement of sensors and effectors is invisible to the evolutionary algorithm. For example,...
Images can be represented as the composition of multiple intrinsic component images, such as shading, albedo, and noise images. In this paper, we present a method for estimating i...
Marshall F. Tappen, Edward H. Adelson, William T. ...
Using a combination of machine learning probabilistic tools, we have shown that some chemistry students fail to develop productive problem solving strategies through practice alon...
Ron Stevens, Amy Soller, Alessandra Giordani, Luca...
Annotating music poses a cognitive load on listeners and this potentially interferes with the emotions being reported. One solution is to let software agents learn to make the ann...
We consider geometric conditions on a labeled data set which guarantee that boosting algorithms work well when linear classifiers are used as weak learners. We start by providing ...