Abstract. The libre software development model has shown how combining collective intelligence can lead to revolutionary methods that underpin major software advancements. This pap...
Hierarchical state decompositions address the curse-ofdimensionality in Q-learning methods for reinforcement learning (RL) but can suffer from suboptimality. In addressing this, w...
Erik G. Schultink, Ruggiero Cavallo, David C. Park...
Many temporal processes can be naturally modeled as a stochastic system that evolves continuously over time. The representation language of continuous-time Bayesian networks allow...
We present a novel method for the discovery and statistical representation of motion patterns in a scene observed by a static camera. Related methods involving learning of pattern...
We describe how to model the appearance of a 3-D object using multiple views, learn such a model from training images, and use the model for object recognition. The model uses pro...