Milos Hauskrecht

Artificial Intelligence · 1998–2017

A researcher in the Science corpus: 7 papers; trusts 47 researchers and is trusted by 55 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 23 citations into it; #5,354 of 35,345 by trust here, #8,810 by citations
• Evaluation & Benchmarks — 10 citations into it
• Reinforcement Learning — 7 citations into it; #1,343 of 2,242 by trust here, #1,241 by citations
• Probabilistic & Bayesian Methods — 6 citations into it; #489 of 1,525 by trust here, #485 by citations
• Statistics and Probability — 6 citations into it

Whom Milos Hauskrecht trusts overall

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

1. Bianca Zadrozny
2. Richard S. Sutton
3. J. Platt
4. Charles Peter Elkan
5. Zoubin Ghahramani
6. Jaume Amores
7. David E. Heckerman
8. Alexandru Niculescu-Mizil
9. Dimitri P. Bertsekas
10. Geoffrey E. Hinton

Who trusts Milos Hauskrecht overall

1. Ronald E. Parr
2. Hideki Asoh
3. C. Drummond
4. Daniel Jaymin Mankowitz
5. Joseph D. Futoma
6. Andrew J. Schaefer
7. Marc Toussaint
8. F. Ingrand
9. Timothy A. Mann
10. Shie Mannor

Papers from Milos Hauskrecht's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Gradient-based learning applied to document recognition
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Learning Multiple Layers of Features from Tiny Images
8. Attention is All you Need (Neural Information Processing Systems)
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Obtaining Well Calibrated Probabilities Using Bayesian Binning (2015) — 1,951 citations
• Planning treatment of ischemic heart disease with partially observable Markov decision processes (2000) — 196 citations
• Binary Classifier Calibration: Non-parametric approach (2014) — 18 citations
• Group-Based Active Learning of Classification Models (2017) — 4 citations
• A Regularized Linear Dynamical System Framework for Multivariate Time Series Analysis (2015) — 35 citations
• Binary Classifier Calibration: Bayesian Non-Parametric Approach (2014)
• Hierarchical Solution of Markov Decision Processes using Macro-actions (1998)