Active learning strategies can be useful when manual labeling
effort is scarce, as they select the most informative
examples to be annotated first. However, for visual category
...
Sudheendra Vijayanarasimhan (University of Texas a...
This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
We consider the problem of estimating the policy gradient in Partially Observable Markov Decision Processes (POMDPs) with a special class of policies that are based on Predictive ...
Kernelizing partial least squares (PLS), an algorithm which has been particularly popular in chemometrics, leads to kernel PLS which has several interesting properties, including ...
Software development is always a challenging undertaking and it requires high commitments from individuals who participate in it. Software development often involves new technolog...