Example-based methods are effective for parameter estimation problems when the underlying system is simple or the dimensionality of the input is low. For complex and high-dimensio...
Gregory Shakhnarovich, Paul A. Viola, Trevor Darre...
We consider the problem of finding a monomial (or a term) that maximizes the agreement rate with a given set of examples over the Boolean hypercube. The problem is motivated by le...
A novel tensor decomposition called pattern or P-decomposition is proposed to make it possible to identify replicating structures in complex data, such as textures and patterns in ...
Anh Huy Phan, Andrzej Cichocki, Petr Tichavsk&yacu...
Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...
It is well known that prior knowledge or bias can speed up learning, at least in theory. It has proved di cult to make constructive use of prior knowledge, so that approximately c...