World's Best Scientists 2026 revealed!

D-Index & Metrics

Mathematics

D-Index
45
Citations
7935
World Ranking
1473
National Ranking
645

Engineering and Technology

D-Index
45
Citations
7499
World Ranking
5529
National Ranking
1546

Overview

Hrushikesh N. Mhaskar is affiliated with Claremont Graduate University in the United States. Their research focuses primarily on computer science, with significant contributions to artificial intelligence, computer vision and pattern recognition, signal processing, statistics and probability, and endocrinology, diabetes and metabolism.

The scientist has published extensively in areas including neural networks and applications, image and signal denoising methods, mathematical approximation and integration, face and expression recognition, numerical methods in inverse problems, statistical methods and inference, and sparse and compressive sensing techniques.

Recent papers authored by Hrushikesh N. Mhaskar include:

  • Function approximation by deep networks (2020) in Communications on Pure & Applied Analysis
  • A Witness Function Based Construction of Discriminative Models Using Hermite Polynomials (2020) in Frontiers in Applied Mathematics and Statistics
  • Local approximation of operators (2023) in Applied and Computational Harmonic Analysis
  • Theory inspired deep network for instantaneous-frequency extraction and signal components recovery from discrete blind-source data (2020) in arXiv (Cornell University)
  • Theory-Inspired Deep Network for Instantaneous-Frequency Extraction and Subsignals Recovery From Discrete Blind-Source Data (2021) in IEEE Transactions on Neural Networks and Learning Systems

Frequent collaborators of Mhaskar include Alexander Cloninger, Tong Mao, Ryan O'Dowd, Sergei V. Pereverzyev, and S. Kitimoon.

Publications are often found in journals and venues such as arXiv (Cornell University), Applied and Computational Harmonic Analysis, Frontiers in Applied Mathematics and Statistics, Neural Networks, and SSRN Electronic Journal.

Best Publications

  • Why and When Can Deep – but Not Shallow – Networks Avoid the Curse of Dimensionality: a Review

    Tomaso A. Poggio;Hrushikesh Mhaskar;Hrushikesh Mhaskar;Lorenzo Rosasco;Brando Miranda

  • Neural networks for optimal approximation of smooth and analytic functions

    H. N. Mhaskar

  • Deep vs. shallow networks: An approximation theory perspective

    Hrushikesh N. Mhaskar;Hrushikesh N. Mhaskar;Tomaso Poggio

  • Approximation by superposition of sigmoidal and radial basis functions

    H.N Mhaskar;Charles A Micchelli

  • Where Does the Sup Norm of a Weighted Polynomial Live? (A Generalization of Incomplete Polynomials)

    H. N. Mhaskar;E. B. Saff

  • Spherical Marcinkiewicz-Zygmund inequalities and positive quadrature

    H. N. Mhaskar;F. J. Narcowich;J. D. Ward

  • Extremal problems for polynomials with exponential weights

    H. N. Mhaskar;E. B. Saff

  • Introduction to the Theory of Weighted Polynomial Approximation

    H N Mhaskar

  • When and Why Are Deep Networks Better Than Shallow Ones

    Hrushikesh Mhaskar;Qianli Liao;Tomaso A. Poggio

  • Approximation properties of a multilayered feedforward artificial neural network

    Hrushikesh Narhar Mhaskar

  • Degree of Approximation by Neural and Translation Networks with a Single Hidden Layer

    H. N. Mhaskar;C. A. Micchelli

  • Learning Functions: When Is Deep Better Than Shallow

    Hrushikesh Mhaskar;Qianli Liao;Tomaso Poggio

  • Fundamentals of Approximation Theory

    Hrushikesh N. Mhaskar;Devidas V. Pai

  • Marcinkiewicz-Zygmund measures on manifolds

    F. Filbir;H. N. Mhaskar

  • A Deep Learning Approach to Diabetic Blood Glucose Prediction

    Hrushikesh N. Mhaskar;Sergei V. Pereverzyev;Maria D. van der Walt

  • A proof of Freud's conjecture for exponential weights

    D. S. Lubinsky;H. N. Mhaskar;E. B. Saff

  • Signal decomposition and analysis via extraction of frequencies

    Charles K. Chui;H.N. Mhaskar;H.N. Mhaskar

  • On trigonometric wavelets

    C. K. Chui;H. N. Mhaskar

  • A deep learning approach to diabetic blood glucose prediction

    H. N. Mhaskar;S. V. Pereverzyev;M. D. van der Walt

  • Limitations of the approximation capabilities of neural networks with one hidden layer

    Charles K. Chui;Xin Li;Hrushikesh Narhar Mhaskar

  • Theory of Deep Learning III: explaining the non-overfitting puzzle

    Tomaso A. Poggio;Kenji Kawaguchi;Qianli Liao;Brando Miranda

Frequent Co-Authors

Charles K. Chui
Charles K. Chui Hong Kong Baptist University
Joseph D. Ward
Joseph D. Ward Texas A&M University
Francis J. Narcowich
Francis J. Narcowich Texas A&M University
Edward B. Saff
Edward B. Saff Vanderbilt University
Charles A. Micchelli
Charles A. Micchelli University at Albany, State University of New York
Ding-Xuan Zhou
Ding-Xuan Zhou University of Sydney
Mauro Maggioni
Mauro Maggioni Johns Hopkins University
Ian H. Sloan
Ian H. Sloan University of New South Wales

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

For students studying Mathematics in the USA, exploring related online degrees can open diverse career opportunities. Many graduates choose to complement their math skills with business knowledge, and options like 1 year MBA programs offer an accelerated path to gain management expertise without a lengthy time commitment.

Flexibility is key for many students, especially those looking to switch programs. It's important to understand if can you transfer MBA programs and how credits can be applied towards your degree. This can save time and money while ensuring a seamless educational journey.

With the rise of big data, pursuing a data analytics masters programs is a popular choice for math graduates aiming to enter tech-driven fields. These programs build advanced analytical skills that are highly sought after in numerous industries.

Additionally, for those concerned about admission competitiveness, identifying easiest MBA programs to get into can help set realistic academic goals without compromising quality education. This approach supports steady career progression tailored to individual circumstances.

Best Scientists Citing Hrushikesh N. Mhaskar

Trending Scientists

Recently Published Articles