Multiple-instance problems arise from the situations where training class labels are attached to sets of samples (named bags), instead of individual samples within each bag (called...
A new class of evolutionary computation processes is presented, called Learnable Evolution Model or LEM. In contrast to Darwinian-type evolution that relies on mutation, recombinat...
In many learning problems prior knowledge about pattern variations can be formalized and beneficially incorporated into the analysis system. The corresponding notion of invarianc...
Abstract. In this paper we study distributed online learning of locomotion gaits for modular robots. The learning is based on a stochastic approximation method, SPSA, which optimiz...
This article proposes a method for learning object templates
composed of local sketches and local textures, and
investigates the relative importance of the sketches and textures
...
Haifeng Gong, Song Chun Zhu, Ying Nian Wu, Zhangzh...