Abstract. The classical perceptron algorithm is an elementary algorithm for solving a homogeneous linear inequality system Ax > 0, with many important applications in learning t...
Alexandre Belloni, Robert M. Freund, Santosh Vempa...
Boosted by the Middlebury challenge, the precision of dense multi-view stereovision methods has increased drastically in the past few years. Yet, most methods, although they perfo...
Vu Hoang Hiep, Renaud Keriven, Patrick Labatut, Je...
An important challenge in the visualization of three dimensional volume data is the e cient processing and rendering of time-resolved sequences. Only the use of compression techni...
The standard approach to the classification of objects is to consider the examples as independent and identically distributed (iid). In many real world settings, however, this ass...
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in paramet...