Recently, Balcan and Blum [1] suggested a theory of learning based on general similarity functions, instead of positive semi-definite kernels. We study the gap between the learnin...
Background: Information obtained from diverse data sources can be combined in a principled manner using various machine learning methods to increase the reliability and range of k...
Bolan Linghu, Evan S. Snitkin, Dustin T. Holloway,...
— Numerical condition affects the learning speed and accuracy of most artificial neural network learning algorithms. In this paper, we examine the influence of opposite transfe...
Functionality-based recognition systems recognize objects at the category level by reasoning about how well the objects support the expected function. Such systems naturally assoc...
In many design tasks it is difficult to explicitly define an objective function. This paper uses machine learning to derive an objective in a feature space based on selected examp...