In reinforcement learning, an agent interacting with its environment strives to learn a policy that specifies, for each state it may encounter, what action to take. Evolutionary c...
Proactive learning is a generalization of active learning designed to relax unrealistic assumptions and thereby reach practical applications. Active learning seeks to select the m...
We propose a method to train a cascade of classifiers by simultaneously optimizing all its stages. The approach relies on the idea of optimizing soft cascades. In particular, inst...
Including mathematical expressions in documents can be a tiresome and difficult process. A recognition system for handwritten mathematical expressions would greatly simplify the t...
John A. Fitzgerald, Franz Geiselbrechtinger, M. Ta...
Simulation has been regarded as the third way to represent social models, alternative to other two symbol systems: the verbal argumentation and the mathematical one. Simulation ca...