The training dynamics of two-layer neural networks with batch normalization (BN) is studied. It written as the a network without BN on Riemannian manifold. Therefore, we identify BN’s effect changing metric in parameter space. Later, infinite-width limit considered, and mean-field formulation derived for dynamics. shown to be Wasserstein gradient flow Theoretical analysis provided well-posednes...

Normalization of expression levels applied to microarray data can help in reducing measurement error. Different methods, including cyclic loess, quantile normalization and median or mean normalization, have been utilized to normalize microarray data. Although there is considerable literature regarding normalization techniques for mRNA microarray data, there are no publications comparing normali...

Autocorrelation domain is a proper domain for clean speech signal and noise separation. In this paper, a method is proposed to decrease effects of noise on the clean speech signal, autocorrelation-based noise subtraction (ANS). Then to deal with the error introduced by assumption that noise and clean speech signal are uncorrelated, two methods are proposed. Also to improve recognition rate of s...

This paper addresses the problem of speaker verification in the presence of additive noise. We propose a fast implementation of Psychoacoustic Model Compensation (Psy-Comp) scheme for static features along with model domain mean and variance normalization for robust speaker recognition in noisy conditions. The proposed algorithms are validated through experiments on noise corrupted NIST-2000 sp...

BACKGROUND AND OBJECTIVE The purpose of this study is to use automated multiple retinal layer segmentation to compare retinal layer intensity profiles between different spectral-domain optical coherence tomography (SD-OCT) devices with and without normalization. PATIENTS AND METHODS A graph-based multistage segmentation approach was used to identify 11 boundaries in horizontal SD-OCT B-scans ...

Short Title: Data-driven intensity normalization in PET group comparisons ABSTRACT Background: Global mean (GM) normalization is one of the most commonly used

The Mel Frequency cepstral coefficients are the most widely used feature in speech recognition but they are very sensitive to noise. In this paper to achieve a satisfactorily performance in Automatic Speech Recognition (ASR) applications we introduce a noise robust new set of MFCC vector estimated through following steps. First, spectral mean normalization is a pre-processing which applies to t...

It is commonly acknowledged that the presence of additive and convolutional noise and speech level variations can seriously deteriorate the performance of a speech recognizer. In case an auditory model is used as the acoustic front-end, it turns out that compensation techniques such as spectral subtraction and log-spectral mean subtraction can be outperformed by time-domain techniques operating...