Sanjoy Dasgupta
Artificial Intelligence · 2000–2020
A researcher in the Science corpus: 24 papers; trusts 225 researchers and is trusted by 481 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 101 citations into it; #1,628 of 36,961 by trust here, #3,488 by citations
- Computer Vision and Pattern Recognition — 70 citations into it; #14,681 of 21,973 by trust here, #14,470 by citations
- Computational Theory and Mathematics — 26 citations into it; #850 of 12,489 by trust here, #1,497 by citations
- Signal Processing — 23 citations into it; #418 of 7,592 by trust here, #634 by citations
- Computer Graphics and Computer-Aided Design — 19 citations into it; #316 of 1,641 by trust here, #410 by citations
- Information Systems — 18 citations into it; #5,553 of 9,233 by trust here, #7,803 by citations
- Statistical Learning Theory — 17 citations into it
- Evaluation & Benchmarks — 16 citations into it
Whom Sanjoy Dasgupta trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Steve Hanneke
- Maria-Florina Balcan
- Dana Angluin
- David A. Cohn
- Yoav Freund
- Alina Beygelzimer
- Hanan Samet
- J. Langford
- Martin A. Zinkevich
- Josh Tenenbaum
Who trusts Sanjoy Dasgupta overall
- Maria-Florina Balcan
- Burr Settles
- Steve Hanneke
- Daniel J. Hsu
- Zhi-Hua Zhou
- Avrim Blum
- Alina Beygelzimer
- Kari Torkkola
- Csaba Szepesvari
- Ran Gilad-Bachrach
Papers from Sanjoy Dasgupta's perspective
Ordered by how strongly the researchers Sanjoy Dasgupta trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Gradient-based learning applied to document recognition
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Learning Multiple Layers of Features from Tiny Images
- Going deeper with convolutions
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Off-Policy Temporal Difference Learning with Function Approximation (2001) — 440 citations
- Importance weighted active learning (2008) — 371 citations
- PAC Generalization Bounds for Co-training (2001) — 339 citations
- Random projection trees and low dimensional manifolds (2008) — 471 citations
- Analysis of Perceptron-Based Active Learning (2009) — 300 citations
- Two faces of active learning (2011) — 336 citations
- Hierarchical sampling for active learning (2008) — 526 citations
- A Non-Parametric Test to Detect Data-Copying in Generative Models (2020) — 76 citations
- A learning framework for nearest neighbor search (2007) — 40 citations
- Teaching a black-box learner (2019) — 55 citations
- The Fast Convergence of Incremental PCA (2013) — 148 citations
- Which Spatial Partition Trees are Adaptive to Intrinsic Dimension? (2009) — 85 citations
- A neural algorithm for a fundamental computing problem (2017) — 238 citations
- Randomized Partition Trees for Nearest Neighbor Search (2015) — 64 citations
- Randomized partition trees for exact nearest neighbor search (2013) — 86 citations
- Classification Accuracies of Physical Activities Using Smartphone Motion Sensors (2012) — 334 citations
- Adaptive Control Processes (2010) — 751 citations
- On-Line Estimation with the Multivariate Gaussian Distribution (2007) — 32 citations
- A General Agnostic Active Learning Algorithm (2007) — 334 citations
- Coarse sample complexity bounds for active learning (2005) — 331 citations