scispace - formally typeset
B

Blaise Aguera y Arcas

Researcher at Google

Publications -  99
Citations -  12926

Blaise Aguera y Arcas is an academic researcher from Google. The author has contributed to research in topics: Pixel & Computer science. The author has an hindex of 28, co-authored 94 publications receiving 7990 citations. Previous affiliations of Blaise Aguera y Arcas include Princeton University & Microsoft.

Papers
More filters
Posted Content

Communication-Efficient Learning of Deep Networks from Decentralized Data

TL;DR: This work presents a practical method for the federated learning of deep networks based on iterative model averaging, and conducts an extensive empirical evaluation, considering five different model architectures and four datasets.
Proceedings Article

Communication-Efficient Learning of Deep Networks from Decentralized Data

TL;DR: In this paper, the authors presented a decentralized approach for federated learning of deep networks based on iterative model averaging, and conduct an extensive empirical evaluation, considering five different model architectures and four datasets.
Posted Content

Federated Learning of Deep Networks using Model Averaging

TL;DR: This work presents a practical method for the federated learning of deep networks that proves robust to the unbalanced and non-IID data distributions that naturally arise, and allows high-quality models to be trained in relatively few rounds of communication.
Journal ArticleDOI

Response regulator output in bacterial chemotaxis

TL;DR: The result indicates that the high sensitivity of the chemotaxis system is not derived from highly cooperative interactions between P‐CheY and the flagellar motor, but rather depends on nonlinear effects within the Chemotaxis signal transduction network.