This article is based on the paper “Meta-Graph: Few Shot Link Prediction via Meta Learning” by Joey Bose, Ankit Jain, Piero Molino, and William L. Hamilton
Many real-world data sets are structured as graphs, and as such, machine …
The post Meta-Graph: Few-Shot Link Prediction Using Meta-Learning appeared first on Uber Engineering Blog.
Experimentation is one of humanity’s principal tools for learning about our complex world. Advances in knowledge from medicine to psychology require a rigorous, iterative process in which we formulate hypotheses and test them by collecting and analyzing new evidence. At …
The post Announcing a New Framework for Designing Optimal Experiments with Pyro appeared first on Uber Engineering Blog.
Jeff Clune and Kenneth Stanley were co-senior authors on this work and our associated research paper.
Machine learning (ML) powers many technologies and services that underpin Uber’s platforms, and we invest in advancing fundamental ML research and engaging with …
The post Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions appeared first on Uber Engineering Blog.
As Uber experienced exponential growth over the last few years, now supporting 14 million trips each day, our engineers proved they could build for scale. That value extends to other areas, including Uber ATG (Advanced Technologies Group) and its quest …
The post Under the Hood of Uber ATG’s Machine Learning Infrastructure and Versioning Control Platform for Self-Driving Vehicles appeared first on Uber Engineering Blog.
With operations in over 700 cities worldwide and gross bookings of over $16 billion in Q3 2019 alone, Uber leverages forecast models to ensure accurate financial planning and budget management. These models, derived from data science practices and platformed for …
The post Building a Backtesting Service to Measure Model Performance at Uber-scale appeared first on Uber Engineering Blog.
Artificial intelligence powers many of the technologies and services underpinning Uber’s platform, allowing engineering and data science teams to make informed decisions that help improve user experiences for products across our lines of business.
At the forefront of this effort …
The post Uber AI in 2019: Advancing Mobility with Artificial Intelligence appeared first on Uber Engineering Blog.
Kenneth O. Stanley and Jeff Clune served as co-senior authors of this article and its corresponding paper.
At Uber, many of the hard problems we work on can benefit from machine learning, such as improving safety, improving ETAs, …
The post Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data appeared first on Uber Engineering Blog.
This article is based on the paper “Plug and Play Language Models: A Simple Approach To Controlled Text Generation” by Sumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung, Eric Frank, Piero Molino, Jason Yosinski, and Rosanne Liu.
The …
The post Controlling Text Generation with Plug and Play Language Models appeared first on Uber Engineering Blog.
The Uber Eats app serves as a portal to more than 320,000 restaurant-partners in over 500 cities globally across 36 countries. In order to make the user experience more seamless and easy-to-navigate, we show users the dishes, restaurants, and cuisines …
The post Food Discovery with Uber Eats: Using Graph Learning to Power Recommendations appeared first on Uber Engineering Blog.
At Uber, we pursue fundamental research to push the frontiers of machine learning, and we endeavor to reduce the latest ML advances to practice, both of which enable us to more effectively ignite opportunity by setting the world in motion.…
The post Uber Goes to NeurIPS 2019 appeared first on Uber Engineering Blog.
