Data Set Used
Smoothness regularization is a popular method to decrease generalization error. We propose a novel regularization technique that rewards local distributional smoothness (LDS), a KL-distance based measure of the model's robustness against perturbation. The LDS is defined in terms of the direction to which the model distribution is most sensitive in the input… (More)
Independent component analysis (ICA) is currently the most popularly used approach to blind source separation (BSS), the problem of recovering unknown source signals when their mixtures are observed but the actual mixing process is unknown. Many ICA algorithms assume that a fixed set of source signals consistently exists in mixtures throughout the… (More)
Polarized neurites (axons and dendrites) form the functional circuitry of the nervous system. Secreted guidance cues often control the polarity of neuron migration and neurite outgrowth by regulating ion channels. Here, we show that secreted semaphorin 3A (Sema3A) induces the neurite identity of Xenopus spinal commissural interneurons (xSCINs) by activating… (More)
This study deals with a reconstruction-type superresolution problem and the accompanying image registration problem simultaneously. We propose a Bayesian approach in which the prior is modeled as a compound Gaussian Markov random field (MRF) and marginalization is performed over unknown variables to avoid overfitting. Our algorithm not only avoids… (More)
increase SLE incidence in Louisiana, and if it did increase incidence in Mis-sissippi, the increase was minimal. In both 2003 and 2004, Louisi-ana's median reporting time to Ar-boNET was ≈30 days. In 2005, the median reporting time prehurricane was 36 days and posthurricane was 69 days. Louisiana state offi cials believed that this reporting lag was largely… (More)
We propose a framework for expanding a given image using an interpolator that is trained <i>in advance</i> with training data, based on sparse Bayesian estimation for determining the optimal and compact support for efficient image expansion. Experiments on test data show that learned interpolators are compact yet superior to classical ones.