This paper presents a method of vision-based reinforcement learning by which a robot learns to shoot a ball into a goal, and discusses several issues in applying the reinforcement...
Local minima and plateaus pose a serious problem in learning of neural networks. We investigate the hierarchical geometric structure of the parameter space of three-layer perceptr...
Spectral analysis approaches have been actively studied in machine learning and data mining areas, due to their generality, efficiency, and rich theoretical foundations. As a natur...
Dijun Luo, Heng Huang, Chris H. Q. Ding, Feiping N...
Tomography is a powerful technique for three-dimensional imaging, that deals with image reconstruction from a series of projection images, acquired along a range of viewing directi...
Sander van der Maar, Kees Joost Batenburg, Jan Sij...
We study the classes of B¨uchi and Rabin automatic structures. For B¨uchi (Rabin) automatic structures their domains consist of infinite strings (trees), and the basic relation...
Greg Hjorth, Bakhadyr Khoussainov, Antonio Montalb...