L
Laurens van der Maaten
Researcher at Facebook
Publications - 127
Citations - 79845
Laurens van der Maaten is an academic researcher from Facebook. The author has contributed to research in topics: Computer science & Network architecture. The author has an hindex of 47, co-authored 118 publications receiving 54188 citations. Previous affiliations of Laurens van der Maaten include Maastricht University & Delft University of Technology.
Papers
More filters
Journal ArticleDOI
Introduction to the special issue on visual analytics using multidimensional projections
Posted Content
Measuring Data Leakage in Machine-Learning Models with Fisher Information
TL;DR: In this paper, the authors proposed Fisher information loss, which measures the amount of information leakage from the model itself or the predictions made by the model about the data by quantifying the Fisher information of the model.
Proceedings Article
Discussion of “Spectral Dimensionality Reduction via Maximum Entropy”
TL;DR: Since the introduction of LLE (Roweis and Saul, 2000) and Isomap (Tenenbaum et al., 2000), a large number of non-linear dimensionality reduction techniques (manifold learners) have been proposed and can be viewed as instantiations of Kernel PCA.
Posted Content
CrypTen: Secure Multi-Party Computation Meets Machine Learning
Brian Knott,Shobha Venkataraman,Awni Hannun,Shubho Sengupta,Mark Ibrahim,Laurens van der Maaten +5 more
TL;DR: In this article, the authors present CrypTen, a software framework that exposes secure MPC primitives via abstractions that are common in modern machine learning frameworks, such as tensor computations, automatic differentiation, and modular neural networks.
GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition
Vikram V. Ramaswamy,Sing Yu Lin,Dora Zhao,Aaron Adcock,Laurens van der Maaten,Deepti Ghadiyaram,Olga Russakovsky +6 more
TL;DR: GeoDE as mentioned in this paper is a geographically diverse dataset with 61,940 images from 40 classes and 6 world regions, and no personally identifiable information, collected through crowd-sourcing, and analyzes differences in images collected in this manner compared to web-scraping.