A
Andrew Y. Ng
Researcher at Stanford University
Publications - 356
Citations - 184387
Andrew Y. Ng is an academic researcher from Stanford University. The author has contributed to research in topics: Deep learning & Supervised learning. The author has an hindex of 130, co-authored 345 publications receiving 164995 citations. Previous affiliations of Andrew Y. Ng include Max Planck Society & Baidu.
Papers
More filters
Proceedings Article
Evaluating the Disentanglement of Deep Generative Models through Manifold Topology
TL;DR: This article proposed a method for quantifying disentanglement that only uses the generative model, by measuring the topological similarity of conditional submanifolds in the learned representation.
Journal Article
Reinforcement learning and apprenticeship learning for robotic control
TL;DR: This work uses apprenticeship learning—in which the authors learn from a human demonstration of a task—as a unifying theme, and presents formal results showing how many control problems can be efficiently addressed given access to a demonstration.
Journal ArticleDOI
Data augmentation with Mobius transformations
TL;DR: In this paper, a novel method of applying Mobius transformations to augment input images during training is presented, which can operate on the sample level and preserve data labels, enabling improved generalization over prior sample-level data augmentation techniques such as cutout and standard crop-and-flip transformations.
Proceedings ArticleDOI
A Graphical Framework for Contextual Search and Name Disambiguation in Email
TL;DR: A canopy for mounting over articles to be protected (vegetables) includes a U-shape main frame having stakes for driving into the ground at a building, and shield including bows, cooperating with the main frame, carrying a flexible covering.
Posted Content
Driverseat: Crowdstrapping Learning Tasks for Autonomous Driving.
Pranav Rajpurkar,Toki Migimatsu,Jeff Kiske,Royce Cheng-Yue,Sameep Tandon,Tao Wang,Andrew Y. Ng +6 more
TL;DR: Driverseat, a technology for embedding crowds around learning systems for autonomous driving, is introduced and it is demonstrated how Driverseat can crowdstrap a convolutional neural network on the lane-detection task.