Learn 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)
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)
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)
We propose a novel regularization technique for supervised and semi-supervised training of large models like deep neural network. By including into objective function the local smoothness of predictive distribution around each training data point, not only were we able to extend the work of (Goodfellow et al. (2015)) to the setting of semi-supervised(More)
A pure tone evokes propagating activities in a strip of the primary auditory cortex (AI), an isofrequency strip (IS). A fundamental issue concerns the roles that thalamocortical input and intracortical connectivity play in generating the activities. Here we addressed this issue in guinea pigs using in vivo and in vitro real-time optical imaging techniques.(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)