Optimally designing the location of training input points (active learning) and choosing the best model (model selection) are two important components of supervised learning and h...
In this paper, we propose two novel methods for face recognition under arbitrary unknown lighting by using spherical harmonics illumination representation, which require only one t...
Background: Most predictive methods currently available for the identification of protein secretion mechanisms have focused on classically secreted proteins. In fact, only two met...
Daniel Restrepo-Montoya, Camilo Pino, Luis F. Ni&n...
This work provides an analysis of using the evolutionary algorithm EPNet to create ensembles of artificial neural networks to solve a range of forecasting tasks. Several previous...
The prediction of collisions amongst N rigid objects may be reduced to a series of computations of the time to first contact for all pairs of objects. Simple enclosing bounds and...