In this paper, we propose a learning method that updates a synaptic weight in probability which is proportional to an output error. Proposed method can reduce computational complexity of learning and at the same time, it can improve the classification ability. We point out that an example produces small output error does not contribute to update of a synaptic weight. As learning progresses, the...

Clinically used low molecular weight heparins (LMWH) are anticoagulants of choice and are phenomenally complex mixtures of millions of distinct natural and unnatural polymeric sequences. The FDA recommends that each LMWH be considered as an independent drug with its own activity profile, placing significant importance on the biophysical characterization of each intact LMWH. We report a robust p...

A well-known theorem of Spencer shows that any set system with n sets over n elements admits a coloring of discrepancy O( √ n). While the original proof was non-constructive, recent progress brought polynomial time algorithms by Bansal, Lovett and Meka, and Rothvoss. All those algorithms are randomized, even though Bansal’s algorithm admitted a complicated derandomization. We propose an elegant...

was initially intended for computing a " quick and dirty " estimate for , which could be used as an initial value for doing a full search using cross validation. The initial estimate, however, turned out to be essentially as good as the final , which rendered further search unneccesary! Another finding that came out of this work, is the fact that guessing the weight decay parameter to be approx...

We apply the holonomic gradient method to compute the distribution function of a weighted sum of independent noncentral chi-square random variables. It is the distribution function of the squared length of a multivariate normal random vector. We treat this distribution as an integral of the normalizing constant of the Fisher-Bingham distribution on the unit sphere and make use of the partial di...

Consider a root system of type BC1 on the real line R with general positive multiplicities. The Cherednik-Opdam transform defines a unitary operator from an L-space on R to a L-space of C-valued functions on R with the Harish-Chandra measure |c(λ)|dλ. By introducing a weight function of the form cosh(t) tanh t on R we find an orthogonal basis for the L-space on R consisting of even and odd func...

The Jacobi polynomials on the simplex are orthogonal polynomials with respect to the weight function Wγ(x) = x γ1 1 · · ·x γd d (1− |x|)d+1 when all γi > −1 and they are eigenfunctions of a second order partial differential operator Lγ . The singular cases that some, or all, γ1, . . . , γd+1 are −1 are studied in this paper. Firstly a complete basis of polynomials that are eigenfunctions of Lγ ...

Due to a high percentage of the bad pixels in small baseline stereo matching method, a small baseline stereo matching method based on adaptive weight is proposed. Firstly, the size of reference window is adaptively calculated for each reference point and then matching costs is evaluated according to adaptive weights and reference window size. Secondly, winner take all is used to evaluate initia...

This study was designed to compare the performance of a new weight estimation strategy (Mercy Method) with 12 existing weight estimation methods (APLS, Best Guess, Broselow, Leffler, Luscombe-Owens, Nelson, Shann, Theron, Traub-Johnson, Traub-Kichen) in children from India. Otherwise healthy children, 2 months to 16 years, were enrolled and weight, height, humeral length (HL), and mid-upper arm...