Philip M. Long
Artificial Intelligence · 1996–2019
A researcher in the Science corpus: 22 papers; trusts 806 researchers and is trusted by 129 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 270 citations into it; #3,077 of 36,961 by trust here, #4,278 by citations
- Optimization & Training — 84 citations into it; #1,213 of 2,605 by trust here, #1,664 by citations
- Statistical Learning Theory — 70 citations into it; #464 of 1,040 by trust here, #521 by citations
- Computer Vision and Pattern Recognition — 67 citations into it; #6,718 of 21,973 by trust here, #7,659 by citations
- Scaling & Learning Theory — 56 citations into it; #157 of 429 by trust here, #242 by citations
- Computational Theory and Mathematics — 48 citations into it; #1,658 of 12,489 by trust here, #1,724 by citations
- Statistics and Probability — 35 citations into it
- Computational Mechanics — 32 citations into it; #1,263 of 10,021 by trust here, #1,365 by citations
Whom Philip M. Long trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Leslie G. Valiant
- Peter L. Bartlett
- Tong Zhang
- Yann LeCun
- L. Eon Bottou
- Kaiming He
- Michael Kearns
- Alex Krizhevsky
Who trusts Philip M. Long overall
- Zhi-Hua Zhou
- Niladri S. Chatterji
- David P. Helmbold
- Boris Babenko
- Stuart Andrews
- Behnam Neyshabur
- Charu C. Aggarwal
- Yu Zhang
- Ilias Diakonikolas
- Hanie Sedghi
Papers from Philip M. Long's perspective
Ordered by how strongly the researchers Philip M. Long trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Benign overfitting in linear regression (2019) — 961 citations
- Gradient Descent with Identity Initialization Efficiently Learns Positive-Definite Linear Transformations by Deep Residual Networks (2018) — 125 citations
- Learning Halfspaces with Malicious Noise (2009) — 145 citations
- Random classification noise defeats all convex potential boosters (2008) — 295 citations
- The power of localization for efficiently learning linear separators with noise (2013) — 224 citations
- Reinforcement Learning with Immediate Rewards and Linear Hypotheses (2003) — 130 citations
- Size-free generalization bounds for convolutional neural networks (2019) — 27 citations
- On the difficulty of approximately maximizing agreements (2000) — 173 citations
- Representing smooth functions as compositions of near-identity functions with implications for deep network optimization (2018) — 34 citations
- Online Learning of Multiple Tasks with a Shared Loss (2007) — 75 citations
- On the inductive bias of dropout (2014) — 74 citations
- Online Multitask Learning (2006) — 81 citations
- Consistency versus Realizable H-Consistency for Multiclass Classification (2013) — 58 citations
- The Singular Values of Convolutional Layers (2018) — 225 citations
- Breast cancer classification and prognosis based on gene expression profiles from a population-based study (2003) — 2,085 citations
- Generalization bounds for deep convolutional neural networks (2019) — 102 citations
- Surprising properties of dropout in deep networks (2016) — 37 citations
- Active and passive learning of linear separators under log-concave distributions (2012) — 157 citations
- Restricted Boltzmann Machines are Hard to Approximately Evaluate or Simulate (2010) — 87 citations
- Attribute-efficient learning of decision lists and linear threshold functions under unconcentrated distributions (2006) — 17 citations