Search Results - "Mhaskar, Hrushikesh N."

Kernel-Based Analysis of Massive Data by Mhaskar, Hrushikesh N.

“…Dealing with massive data is a challenging task for machine learning. An important aspect of machine learning is function approximation. In the context of…”
Get full text

A Deep Learning Approach to Diabetic Blood Glucose Prediction by Mhaskar, Hrushikesh N., Pereverzyev, Sergei V., van der Walt, Maria D.

“…We consider the question of 30-min prediction of blood glucose levels measured by continuous glucose monitoring devices, using clinical data. While most…”
Get full text

Deep Nets for Local Manifold Learning by Chui, Charles K., Mhaskar, Hrushikesh N.

“…The problem of extending a function f defined on a training data C on an unknown manifold 𝕏 to the entire manifold and a tubular neighborhood of this manifold…”
Get full text

Kernel Distance Measures for Time Series, Random Fields and Other Structured Data by Das, Srinjoy, Mhaskar, Hrushikesh N., Cloninger, Alexander

“…This paper introduces kdiff, a novel kernel-based measure for estimating distances between instances of time series, random fields and other forms of…”
Get full text

A Witness Function Based Construction of Discriminative Models Using Hermite Polynomials by Mhaskar, Hrushikesh N., Cheng, Xiuyuan, Cloninger, Alexander

“…In machine learning, we are given a dataset of the form {(xj,yj)}j=1M, drawn as i.i.d. samples from an unknown probability distribution μ; the marginal…”
Get full text

Applications of classical approximation theory to periodic basis function networks and computational harmonic analysis by Mhaskar, Hrushikesh N., Nevai, Paul, Shvarts, Eugene

“…In this paper, we describe a novel approach to classical approximation theory of periodic univariate and multivariate functions by trigonometric polynomials…”
Get full text

Filtered Legendre expansion method for numerical differentiation at the boundary point with application to blood glucose predictions by Mhaskar, Hrushikesh N., Naumova, V., Pereverzyev, S.V.

“…Let f:[-1,1]→R be continuously differentiable. We consider the question of approximating f′(1) from given data of the form (tj,f(tj))j=1M where the points tj…”
Get full text

Kernel based analysis of massive data by Mhaskar, Hrushikesh N

“…Dealing with massive data is a challenging task for machine learning. An important aspect of machine learning is function approximation. In the context of…”
Get full text

Dimension independent bounds for general shallow networks by Mhaskar, Hrushikesh N

“…This paper proves an abstract theorem addressing in a unified manner two important problems in function approximation: avoiding curse of dimensionality and…”
Get full text

Inversion of the Laplace Transform of Point Masses by McKenna, Michael, Mhaskar, Hrushikesh N, Spencer, Richard G

“…Motivated by applications in magnetic resonance relaxometry, we consider the following problem: Given samples of a function $t\mapsto \sum_{k=1}^K…”
Get full text

Function approximation with zonal function networks with activation functions analogous to the rectified linear unit functions by Mhaskar, Hrushikesh N

“…A zonal function (ZF) network on the $q$ dimensional sphere $\mathbb{S}^q$ is a network of the form $\mathbf{x}\mapsto \sum_{k=1}^n…”
Get full text

Approximate quadrature measures on data--defined spaces by Mhaskar, Hrushikesh N

“…An important question in the theory of approximate integration is to study the conditions on the nodes $x_{k,n}$ and weights $w_{k,n}$ that allow an estimate…”
Get full text

A unified framework for harmonic analysis of functions on directed graphs and changing data by Mhaskar, Hrushikesh N

“…We present a general framework for studying harmonic analysis of functions in the settings of various emerging problems in the theory of diffusion geometry…”
Get full text

Stable soft extrapolation of entire functions by Batenkov, Dmitry, Demanet, Laurent, Mhaskar, Hrushikesh N

“…Soft extrapolation refers to the problem of recovering a function from its samples, multiplied by a fast-decaying window and perturbed by an additive noise,…”
Get full text

Deep Algorithms: designs for networks by Rajagopal, Abhejit, Chandrasekaran, Shivkumar, Mhaskar, Hrushikesh N

“…A new design methodology for neural networks that is guided by traditional algorithm design is presented. To prove our point, we present two heuristics and…”
Get full text

Theory inspired deep network for instantaneous-frequency extraction and signal components recovery from discrete blind-source data by Chui, Charles K, Han, Ningning, Mhaskar, Hrushikesh N

“…This paper is concerned with the inverse problem of recovering the unknown signal components, along with extraction of their instantaneous frequencies (IFs),…”
Get full text

A Fourier-invariant method for locating point-masses and computing their attributes by Chui, Charles K, Mhaskar, Hrushikesh N

“…Motivated by the interest of observing the growth of cancer cells among normal living cells and exploring how galaxies and stars are truly formed, the…”
Get full text

A unified method for super-resolution recovery and real exponential-sum separation by Chui, Charles K, Mhaskar, Hrushikesh N

“…In this paper, motivated by diffraction of traveling light waves, a simple mathematical model is proposed, both for the multivariate super-resolution problem…”
Get full text