At Uber, magical customer experiences depend on accurate arrival time predictions (ETAs). We use ETAs to calculate fares, estimate pickup times, match riders to...
Introduction Uber is a worldwide marketplace of services, processing thousands of monetary transactions every second. As a marketplace, Uber takes on all of the risks...
Introduction Capacity is a key component of reliability. Uber's services require enough resources in order to handle daily peak traffic and to support our different...
Introduction Since we productionized distributed XGBoost on Apache Spark™ at Uber in 2017, XGBoost has powered a wide spectrum of machine learning (ML) use cases...
Project Homepage: GitHub Over the past several years, increasing processing power of computing machines has led to an increase in machine learning advances. More and...
Developed by Uber ATG, Neuropod is an abstraction layer that provides a universal interface to run models across any deep learning framework.
Uber ATG's self-driving vehicles measure a multitude of possible scenario variations to answer the age-old question: "how does the pedestrian cross the road?"
Uber AI introduces Meta-Graph, a new few-shot link prediction framework that facilitates the more accurate training of ML models that quickly adapt to new graph data.
Uber AI released a new framework on top of Pyro that lets experimenters seamlessly automate optimal experimental design (OED) for quicker model iteration.
Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
Building upon our existing open-ended learning research, Uber AI released Enhanced POET, a project that incorporates an improved algorithm and allows for more diverse training environments.
Managing multiple machine learning models to enable self-driving vehicles is a challenge. Uber ATG developed a model life cycle for quick iterations and a tool for continuous delivery and dependency management.
We built a backtesting service to better assess financial forecast model error rates, facilitating improved forecast performance and decision making.
In 2019, Uber AI built tools and systems that leverage ML to improve location accuracy and enhance real-time forecasting, among other applications on our platform.
Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
Developed by Uber AI Labs, Generative Teaching Networks (GTNs) automatically generate training data, learning environments, and curricula to help AI agents rapidly learn.
Plug and Play Language Model, introduced by Uber AI Labs, gives NLP practitioners the flexibility to plug in one or more simple attribute models into a large, unconditional language model.
By integrating graph learning techniques with our Uber Eats recommendation system, we created a more seamless and individualized user experience for eaters on our platform.
Uber is presenting 11 papers at the NeurIPS 2019 conference in Vancouver, Canada, as well as sponsoring workshops including Women in Machine Learning (WiML) and Black in AI.
Uber's 2020 AI Residency will focus on initiatives related to our self-driving car project through Uber Advanced Technology Group (ATG).
Attending ICCV, CoRL, or IROS 2019? Learn about Uber ATG's recent research in artificial intelligence by checking out our workshops, posters, and keynotes.
To accommodate additional ML use cases, Uber evolved Michelangelo's application of the Apache Spark MLlib library for greater flexibility and extensibility.