Hrushikesh Narhar Mhaskar

Artificial Intelligence · 2000–2017

A researcher in the Science corpus: 11 papers; trusts 73 researchers and is trusted by 29 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 42 citations into it; #7,107 of 35,345 by trust here, #6,664 by citations
• Computer Vision and Pattern Recognition — 38 citations into it; #19,570 of 21,575 by trust here, #18,266 by citations
• Scaling & Learning Theory — 20 citations into it
• Model Architectures — 17 citations into it
• Optimization & Training — 16 citations into it
• Representation & Self-Supervised Learning — 14 citations into it
• Applied Mathematics — 12 citations into it; #3,564 of 7,620 by trust here, #4,234 by citations
• Computational Theory and Mathematics — 12 citations into it

Whom Hrushikesh Narhar Mhaskar trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Tomaso A. Poggio
2. Maximilian Riesenhuber
3. Yoshua Bengio
4. J. Håstad
5. Allan Pinkus
6. Martin H. Anthony
7. Kaiming He
8. Andrea Vedaldi
9. Yann LeCun
10. Andrew R. Barron

Who trusts Hrushikesh Narhar Mhaskar overall

1. Dmitry Yarotsky
2. Boris Hanin
3. Mauro Maggioni
4. Frank Filbir
5. S. H. Shabbeer Basha
6. Johannes Schmidt-Hieber
7. Tomaso A. Poggio
8. Max H. Farrell
9. Kenji Kawaguchi
10. Paul Nevai

Papers from Hrushikesh Narhar Mhaskar's perspective

Ordered by how strongly the researchers Hrushikesh Narhar Mhaskar trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Attention is All you Need (Neural Information Processing Systems)
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. Going deeper with convolutions

Their papers

• Deep vs. shallow networks : An approximation theory perspective (2016) — 376 citations
• Theory of Deep Learning III: explaining the non-overfitting puzzle (2017) — 138 citations
• Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review (2016) — 657 citations
• Learning Functions: When Is Deep Better Than Shallow (2016) — 150 citations
• Learning Real and Boolean Functions: When Is Deep Better Than Shallow (2016) — 61 citations
• Applications of classical approximation theory to periodic basis function networks and computational harmonic analysis (2013) — 10 citations
• A Quadrature Formula for Diffusion Polynomials Corresponding to a Generalized Heat Kernel (2010) — 87 citations
• Diffusion polynomial frames on metric measure spaces (2008) — 100 citations
• On the representation of smooth functions on the sphere using finitely many bits (2005) — 48 citations
• Polynomial Frames: A Fast Tour (2004) — 54 citations
• Fundamentals of Approximation Theory (2000) — 85 citations