Shin-ichi Maeda

Learn More
Smoothness regularization is a popular method to decrease generalization error. We propose a novel regularization technique that rewards local distributional smoothness (LDS), a KLdistance 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)
Cyanobacteria possess light-dependent CO2 uptake activity that results in the net hydration of CO2 to HCO3- and may involve a protein-mediated carbonic anhydrase (CA)-like activity. This process is vital for the survival of cyanobacteria and may be a contributing factor in the ecological success of this group of organisms. Here, via isolation of mutants of(More)
The cmp operon of the cyanobacterium Synechococcus elongatus strain PCC 7942, encoding the subunits of the ABC-type bicarbonate transporter, is activated under CO2-limited growth conditions in a manner dependent on CmpR, a LysR family transcription factor of CbbR subfamily. The 0.7 kb long regulatory region of the operon carried a single promoter, which(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)
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)
We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the output distribution. Virtual adversarial loss is defined as the robustness of the model’s posterior distribution against local perturbation around each input data point. Our method is similar to adversarial training, but differs from(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)