Time-to-event modeling is critical to better understanding various dimensions of the user experience. By leveraging censored time-to-event data (data involving time intervals where some of those time intervals may extend beyond when data is analyzed), companies can gain insights on …
The post Modeling Censored Time-to-Event Data Using Pyro, an Open Source Probabilistic Programming Language appeared first on Uber Engineering Blog.
At Uber, hundreds of data scientists, economists, AI researchers and engineers, product analysts, behavioral scientists, and other practitioners leverage scientific methods to solve challenges on our platform. From modeling and experimentation to data analysis, algorithm development, and fundamental research, the …
The post First Uber Science Symposium: Discussing the Next Generation of RL, NLP, ConvAI, and DL appeared first on Uber Engineering Blog.
Over the last decade, deep learning models have proven highly effective at performing a wide variety of machine learning tasks in vision, speech, and language. At Uber we are using these models for a variety of tasks, including customer support…
The post Introducing Ludwig, a Code-Free Deep Learning Toolbox appeared first on Uber Engineering Blog.
Machine learning (ML) is widely used across the Uber platform to support intelligent decision making and forecasting for features such as ETA prediction and fraud detection. For optimal results, we invest a lot of resources in developing accurate predictive …
The post Manifold: A Model-Agnostic Visual Debugging Tool for Machine Learning at Uber appeared first on Uber Engineering Blog.
This research was conducted with valuable help from collaborators at Google Brain and OpenAI.
A selection of trained agents populating the Atari zoo.
Some of the most exciting advances in AI recently have come from the field of deep reinforcement …
The post Creating a Zoo of Atari-Playing Agents to Catalyze the Understanding of Deep Reinforcement Learning appeared first on Uber Engineering Blog.
Jeff Clune and Kenneth O. Stanley were co-senior authors.
We are interested in open-endedness at Uber AI Labs because it offers the potential for generating a diverse and ever-expanding curriculum for machine learning entirely on its own. Having vast amounts …
The post POET: Endlessly Generating Increasingly Complex and Diverse Learning Environments and their Solutions through the Paired Open-Ended Trailblazer appeared first on Uber Engineering Blog.
Neural networks, an important tool for processing data in a variety of industries, grew from an academic research area to a cornerstone of industry over the last few years. Convolutional Neural Networks (CNNs) have been particularly useful for extracting information …
The post Faster Neural Networks Straight from JPEG appeared first on Uber Engineering Blog.
