Jeffrey Mahler

Control and Systems Engineering · 2014–2019

A researcher in the Science corpus: 10 papers; trusts 195 researchers and is trusted by 15 researchers here, as inferred from the citation graph.

Subfields

• Control and Systems Engineering — 111 citations into it; #1,638 of 8,257 by trust here, #190 by citations
• Computer Vision and Pattern Recognition — 106 citations into it
• Artificial Intelligence — 89 citations into it
• Robotics & Control — 55 citations into it; #304 of 609 by trust here, #141 by citations
• Reinforcement Learning — 49 citations into it
• Aerospace Engineering — 48 citations into it
• Biomedical Engineering — 38 citations into it; #4,151 of 10,734 by trust here, #2,001 by citations
• Human-Computer Interaction — 17 citations into it

Whom Jeffrey Mahler trusts overall

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

1. Alex Krizhevsky
2. Geoffrey E. Hinton
3. Kaiming He
4. Jeannette Bohg
5. Sergey Levine
6. Ian Lenz
7. Ilya Sutskever
8. Lerrel Pinto
9. Ross B. Girshick
10. Jonathan Weisz

Who trusts Jeffrey Mahler overall

1. Andy Zeng
2. Douglas Morrison
3. Sergey Levine
4. Arsalan Mousavian
5. Abhinav Kumar Gupta
6. Adithyavairavan Murali
7. Matthew Matl
8. Peter Corke
9. Haoshu Fang
10. Lucas Manuelli

Papers from Jeffrey Mahler's perspective

Ordered by how strongly the researchers Jeffrey Mahler 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. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. ImageNet: A large-scale hierarchical image database
5. Gradient-based learning applied to document recognition
6. Long Short-Term Memory
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. ImageNet Large Scale Visual Recognition Challenge
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Dex-Net 1.0: A cloud-based network of 3D objects for robust grasp planning using a Multi-Armed Bandit model with correlated rewards (2016) — 391 citations
• SHIV: Reducing supervisor burden in DAgger using support vectors for efficient learning from demonstrations in high dimensional state spaces (2016) — 74 citations
• Comparing human-centric and robot-centric sampling for robot deep learning from demonstrations (2016) — 80 citations
• Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics (2017) — 1,418 citations
• Dex-Net 3.0: Computing Robust Vacuum Suction Grasp Targets in Point Clouds Using a New Analytic Model and Deep Learning (2018) — 244 citations
• Learning ambidextrous robot grasping policies (2019) — 602 citations
• Learning accurate kinematic control of cable-driven surgical robots using data cleaning and Gaussian Process Regression (2014) — 84 citations
• Using dVRK teleoperation to facilitate deep learning of automation tasks for an industrial robot (2017) — 28 citations
• Learning Deep Policies for Robot Bin Picking by Simulating Robust Grasping Sequences (2017) — 202 citations
• Dex-Net 3.0: Computing Robust Robot Suction Grasp Targets in Point Clouds using a New Analytic Model and Deep Learning (2017) — 133 citations