Recent work has provided functions that can be used to prove a principled distinction between the capabilities of mutation-based and crossover-based algorithms. However, prior fun...
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
Evolutionary and genetic algorithms (EAs and GAs) are quite successful randomized function optimizers. This success is mainly based on the interaction of different operators like ...
Fast query processing of complex objects, e.g. spatial or uncertain objects, depends on efficient spatial pruning of the objects’ approximations, which are typically minimum bou...
—Approximating ideal program outputs is a common technique for solving computationally difficult problems, for adhering to processing or timing constraints, and for performance ...
Jason Ansel, Yee Lok Wong, Cy P. Chan, Marek Olsze...