Many machine learning algorithms can be formulated as a generalized eigenvalue problem. One major limitation of such formulation is that the generalized eigenvalue problem is comp...
Many learning algorithms rely on the curvature (in particular, strong convexity) of regularized objective functions to provide good theoretical performance guarantees. In practice...
We explore dynamic shaping to integrate our prior beliefs of the final policy into a conventional reinforcement learning system. Shaping provides a positive or negative artificial...
One of the key factors affecting functional MRI image reconstruction is field inhomogeneity. It is desirable to estimate both the distortion-free MRI image and field map simultane...
Hien M. Nguyen, Robert L. Morrison Jr., Bradley P....
Segmentation and tracking of cells in fluorescence microscopy image sequences is an important task in many biological studies into cell migration as well as intracellular dynamics...
Oleh Dzyubachyk, Wiro J. Niessen, Erik H. W. Meije...