Core AI tech

Areas of fundamental machine learning science include sparse and efficient operations for real-time inference, theoretical analysis of the robustness and safety of neural networks, stochastic and non-linear optimization, learning in the presence of noisy biased data, and more.

Recent ATG R&D publications

DSIC: Deep Stereo Image Compression

Jerry Liu, Shenlong Wang, Raquel Urtasun (ICCV 2019, oral)

Graph HyperNetworks for Neural Architecture Search

Chris Zhang, Mengye Ren, Raquel Urtasun (ICLR 2019)

SBNet: Sparse Blocks Network for Fast Inference

Mengye Ren*, Andrei Pokrovsky*, Bin Yang*, Raquel Urtasun (CVPR 2018, spotlight)

Deep Parametric Continuous Convolutional Neural Networks

Shenlong Wang*, Simon Suo*, Wei-Chiu Ma, Andrei Pokrovsky, Raquel Urtasun (CVPR 2018, spotlight)

Matching Adversarial Networks

Gellért Máttyus, Raquel Urtasun (CVPR 2018)

Learning to Reweight Examples for Robust Deep Learning

Mengye Ren, Wenyuan Zeng, Bin Yang, Raquel Urtasun (ICML 2018, spotlight)

R&D Homepage

Back to Homepage

UberX

UberPool

UberXL

Select

Black

WAV

JUMP Bikes

Lux

Black SUV

Flash

JUMP Scooter

UberTuk

Uber Air

Fahrer

Liefern

Bestellung

Liefern

Restaurant-Partner

Geschäftsreisen

Gesponserte Fahrten

Voucher

Health

Transportunternehmer

Spediteur

Core AI tech

Recent ATG R&D publications

DSIC: Deep Stereo Image Compression

Graph HyperNetworks for Neural Architecture Search

SBNet: Sparse Blocks Network for Fast Inference

Deep Parametric Continuous Convolutional Neural Networks

Matching Adversarial Networks

Learning to Reweight Examples for Robust Deep Learning

R&D Homepage