K
Kilian Q. Weinberger
Researcher at Cornell University
Publications - 241
Citations - 71535
Kilian Q. Weinberger is an academic researcher from Cornell University. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 76, co-authored 222 publications receiving 49707 citations. Previous affiliations of Kilian Q. Weinberger include University of Washington & Washington University in St. Louis.
Papers
More filters
Proceedings ArticleDOI
Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
TL;DR: In this paper, the authors argue that it is not the quality of the data but its representation that accounts for the majority of the difference, and propose to convert image-based depth maps to pseudo-LiDAR representations.
Posted Content
On Fairness and Calibration
TL;DR: This paper investigated the tension between minimizing error disparity across different population groups while maintaining calibrated probability estimates and showed that calibration is compatible only with a single error constraint (i.e. equal false negatives rates across groups).
Posted Content
Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
TL;DR: This paper proposes to convert image-based depth maps to pseudo-LiDAR representations --- essentially mimicking the LiDAR signal, and achieves impressive improvements over the existing state-of-the-art in image- based performance.
Journal ArticleDOI
Disruptions of network connectivity predict impairment in multiple behavioral domains after stroke
Joshua S. Siegel,Lenny Ramsey,Abraham Z. Snyder,Nicholas V. Metcalf,Ravi V. Chacko,Kilian Q. Weinberger,Antonello Baldassarre,Carl D. Hacker,Gordon L. Shulman,Maurizio Corbetta +9 more
TL;DR: Key organizational features of brain networks to brain–behavior relationships in stroke are linked to show that visual memory and verbal memory deficits are better predicted by functional connectivity than by lesion location, and visual and motor deficits arebetter predicted by lesions location than functional connectivity.
Proceedings Article
Compressing Neural Networks with the Hashing Trick
TL;DR: HashedNets as discussed by the authors uses a hash function to randomly group connection weights into hash buckets, and all connections within the same hash bucket share a single parameter value, which can be tuned to adjust to the weight sharing architecture with standard backprop during training.