2269 results for "earn" across all locations
Ringing in 2017 in India
After a several New Year’s Eves under our belt, we’ve learned that millions of people in cities around the world rely on Uber for a safe, reliable ride to and from their celebrations. This year, we wanted to spotlight how riders in India used Uber when ringing in the New Year. Check out these 5 fun facts!
Collaboration at Scale: Highlights from Uber Open Summit 2018
Uber hosted its first Open Summit on November 15, inviting the open source community to learn about our open source projects from the engineers who use them every day. Check out highlights from the day, including keynotes from the Linux Foundation’s Jim Zemlin and Uber AI’s Zoubin Ghahramani.
Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask
H. Zhou, J. Lan, R. Liu, J. Yosinski
Optical Character Recognition (OCR) approaches have been widely advanced in recent years thanks to the resurgence of deep learning. The state-of-the-art models are mainly trained on the datasets consisting of the constrained scenes. Detecting and recognizing text from the real-world images remains a technical challenge. […] [PDF]
Conference on Neural Information Processing Systems (NeurIPS), 2019
Pathwise Derivatives Beyond the Reparameterization Trick
M. Jankowiak, F. Obermeyer
We observe that gradients computed via the reparameterization trick are in direct correspondence with solutions of the transport equation in the formalism of optimal transport. We use this perspective to compute (approximate) pathwise gradients for probability distributions not directly amenable to the reparameterization trick: Gamma, Beta, and Dirichlet. […] [PDF]
International Conference on Machine Learning (ICML), 2018
Probabilistic Meta-Representations Of Neural Networks
T. Karaletsos, P. Dayan, Z. Ghahramani
Existing Bayesian treatments of neural networks are typically characterized by weak prior and approximate posterior distributions according to which all the weights are drawn independently. Here, we consider a richer prior distribution in which units in the network are represented by latent variables, and the weights between units are drawn conditionally on the values of the collection of those variables. […] [PDF]
UAI 2018 Uncertainty In Deep Learning Workshop (UDL), 2018
Samsara makes virtual events special with Vouchers for Uber Eats
Samsara makes virtual events special with Vouchers for Uber Eats. Given that Samsara’s internal sales kick-off lunch was just a one-day need, Vouchers for Uber Eats made more sense than an ongoing corporate meal program. Since the success of the SKO, the Samsara team has already started using Vouchers for Uber Eats to connect with employees, customers, and prospects during lunch-and-learns and other virtual events.
Behind the Wheel with…Maureen, NJ uberX Partner
Maureen, a New Jersey native, worked on Wall Street for 31 years until finally she decided that she needed a break. Today, you can find Maureen cruising the streets of New Jersey—from down the shore (where she lives) to Hoboken and Jersey City—driving as one of our highest-rated uberX partners. Learn more about Maureen.
Meet your Portland Drivers
With over 5,000 partners in Portland and counting, it’s nice to take some time and get to know their stories. Through events at our Partner Support Center, volunteer opportunities and partner involvement with UberIMPACT, we’ve learned a bit more about the people who make Uber in Portland possible. Read some of their stories below:
Robustness to out-of-distribution inputs via taskaware generative uncertainty
R. McAllister, G. Kahn, J. Clune, S. Levine
Deep learning provides a powerful tool for machine perception when the observations resemble the training data. However, real-world robotic systems must react intelligently to their observations even in unexpected circumstances. This requires a system to reason about its own uncertainty given unfamiliar, out-of-distribution observations. […] [PDF]
International Conference on Robotics and Automation (ICRA), 2019
A birth-death process for feature allocation
K. Palla, D. Knowles, Z. Ghahramani
We propose a Bayesian nonparametric prior over feature allocations for sequential data, the birthdeath feature allocation process (BDFP). The BDFP models the evolution of the feature allocation of a set of N objects across a covariate (e.g. time) by creating and deleting features. […] [PDF]
International Conference on Machine Learning (ICML), 2017