- Home
- Best Scientists - Mathematics
- Hrushikesh N. Mhaskar

Discipline name
D-index
D-index (Discipline H-index) only includes papers and citation values for an examined
discipline in contrast to General H-index which accounts for publications across all
disciplines.
Citations
Publications
World Ranking
National Ranking

Engineering and Technology
D-index
34
Citations
5,078
89
World Ranking
3656
National Ranking
1407

Mathematics
D-index
43
Citations
6,643
168
World Ranking
1165
National Ranking
538

- Mathematical analysis
- Real number
- Algebra

His primary areas of investigation include Mathematical analysis, Combinatorics, Function, Artificial neural network and Discrete mathematics. His research integrates issues of Universal approximation theorem, Quadrature and Continuous function in his study of Mathematical analysis. His Combinatorics research incorporates themes from Riemannian manifold, Boundary and Exponential function.

The Function study combines topics in areas such as Activation function and Radial basis function network. His Artificial neural network research is multidisciplinary, incorporating elements of Deep learning, Convolutional neural network and Theoretical computer science. His work deals with themes such as Curse of dimensionality and Special case, which intersect with Convolutional neural network.

- Why and When Can Deep – but Not Shallow – Networks Avoid the Curse of Dimensionality: a Review (250 citations)
- Why and When Can Deep – but Not Shallow – Networks Avoid the Curse of Dimensionality: a Review (250 citations)
- Neural networks for optimal approximation of smooth and analytic functions (247 citations)

Hrushikesh N. Mhaskar mainly investigates Mathematical analysis, Function, Combinatorics, Discrete mathematics and Function approximation. He has researched Mathematical analysis in several fields, including Applied mathematics, Quadrature and Pure mathematics. His Function study also includes

- Class most often made with reference to Artificial neural network,
- Activation function together with Radial basis function network.

In his research, Boundary is intimately related to Riemannian manifold, which falls under the overarching field of Combinatorics. The study incorporates disciplines such as Nonlinear dimensionality reduction, Theoretical computer science, Convolutional neural network and Curse of dimensionality in addition to Function approximation. His Theoretical computer science research integrates issues from Deep learning, Cluster analysis and Artificial intelligence.

- Mathematical analysis (34.30%)
- Function (29.47%)
- Combinatorics (20.29%)

- Function (29.47%)
- Function approximation (20.29%)
- Artificial intelligence (12.08%)

Hrushikesh N. Mhaskar spends much of his time researching Function, Function approximation, Artificial intelligence, Curse of dimensionality and Algorithm. Hrushikesh N. Mhaskar has included themes like Smoothness, Smoothness, Discrete mathematics and Metric in his Function study. Hrushikesh N. Mhaskar interconnects Nonlinear dimensionality reduction, Manifold, Activation function and Propagation of uncertainty in the investigation of issues within Function approximation.

His Artificial intelligence research focuses on Machine learning and how it connects with Orthonormal basis, Bounded function and Continuum. His Curse of dimensionality research is multidisciplinary, incorporating perspectives in Artificial neural network and Directed acyclic graph. His Algorithm research is multidisciplinary, relying on both Exponential function, Exponential sum, Simple and Inverse problem.

- Why and When Can Deep – but Not Shallow – Networks Avoid the Curse of Dimensionality: a Review (250 citations)
- When and Why Are Deep Networks Better Than Shallow Ones (74 citations)

- Mathematical analysis
- Algebra
- Real number

Hrushikesh N. Mhaskar focuses on Representation, Function, Artificial intelligence, Deep learning and Algebra. His Representation study combines topics in areas such as Mathematical proof, Smoothness, Mathematical analysis, Real line and Pure mathematics. His research in Function intersects with topics in Discrete mathematics, Structure, Hermite functions and Nonlinear dimensionality reduction.

Many of his research projects under Artificial intelligence are closely connected to Continuous glucose monitoring and Novelty with Continuous glucose monitoring and Novelty, tying the diverse disciplines of science together. His Curse of dimensionality study integrates concerns from other disciplines, such as Theoretical computer science, Convolutional neural network and Special case. The concepts of his Deep learning study are interwoven with issues in Artificial neural network, Function approximation, Gradient descent, Applied mathematics and Data set.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

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.

International Journal of Automation and Computing **(2017)**

453 Citations

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.

International Journal of Automation and Computing **(2017)**

453 Citations

Neural networks for optimal approximation of smooth and analytic functions

H. N. Mhaskar.

Neural Computation **(1996)**

374 Citations

Neural networks for optimal approximation of smooth and analytic functions

H. N. Mhaskar.

Neural Computation **(1996)**

374 Citations

Approximation by superposition of sigmoidal and radial basis functions

H.N Mhaskar;Charles A Micchelli.

Advances in Applied Mathematics **(1992)**

348 Citations

Approximation by superposition of sigmoidal and radial basis functions

H.N Mhaskar;Charles A Micchelli.

Advances in Applied Mathematics **(1992)**

348 Citations

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

H. N. Mhaskar;E. B. Saff.

Constructive Approximation **(1985)**

293 Citations

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

H. N. Mhaskar;E. B. Saff.

Constructive Approximation **(1985)**

293 Citations

Deep vs. shallow networks: An approximation theory perspective

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

Analysis and Applications **(2016)**

288 Citations

Deep vs. shallow networks: An approximation theory perspective

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

Analysis and Applications **(2016)**

288 Citations

Journal of Approximation Theory

(Impact Factor: 0.993)

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

Contact us

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:

Hong Kong Baptist University

MIT

Texas A&M University

Texas A&M University

Vanderbilt University

University of Genoa

University at Albany, State University of New York

City University of Hong Kong

University of New South Wales

Ulsan National Institute of Science and Technology

University of Science and Technology of China

University of Strasbourg

Rovira i Virgili University

University of Geneva

University of California, Davis

Pennsylvania State University

Purdue University West Lafayette

Boyce Thompson Institute

University College Dublin

University of South Florida

Stony Brook University

University of Kentucky

Brigham and Women's Hospital

Brigham and Women's Hospital

Harvard University

Something went wrong. Please try again later.