Learning data representations is a fundamental challenge in modeling neural processes and plays an important role in applications such as object recognition. In multi-stage Optima...
The kernel Perceptron is an appealing online learning algorithm that has a drawback: whenever it makes an error it must increase its support set, which slows training and testing ...
We present a novel loop transformation technique, particularly well suited for optimizing embedded compilers, where an increase in compilation time is acceptable in exchange for s...
The study of common, complex multifactorial diseases in genetic epidemiology is complicated by nonlinearity in the genotype-to-phenotype mapping relationship that is due, in part,...
Ryan J. Urbanowicz, Nate Barney, Bill C. White, Ja...
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...