Uber Engineering created Omphalos, our new backtesting framework, to enable efficient and reliable comparison of forecasting models across languages.
Uber AI Labs proposes Loss Change Allocation (LCA), a new method that provides a rich window into the neural network training process.
Uber AI Labs introduces a method for making neural networks that process images faster and more accurately by leveraging JPEG representations.
To improve our maps, Uber Engineering analyzes customer support tickets with natural language processing and deep learning to identify and correct inaccurate map data.
Uber's Marketplace simulation platform leverages ML to rapidly prototype and test new product features and hypotheses in a risk-free environment.
Metropolis-Hastings Generative Adversarial Networks (GANs) leverage the discriminator to pick better samples from the generator after ML model training is done.
Uber AI Labs releases EvoGrad, a library for catalyzing gradient-based evolution research, and Evolvability ES, a new meta-learning algorithm enabled by this library.
Uber engineers offer two common use cases showing how we orchestrate machine learning model training in our data workflow engine.
Uber's Chief Scientist announces the launch of the Uber Research Publications Site, a portal for showcasing our contributions to the research community.
The Uber Science Symposium featured talks from members of the broader scientific community about the the latest innovations in RL, NLP, and other fields.
Uber AI's Piero Molino discusses Ludwig's origin story, common use cases, and how others can get started with this powerful deep learning framework built on top of TensorFlow.
Applying hardware acceleration to deep neuroevolution in what is now an open source project, Uber AI Labs was able to train a neural network to play Atari in just a few hours on a single personal computer, making this type of research accessible to a far greater number of people.
To accommodate additional ML use cases, Uber evolved Michelangelo's application of the Apache Spark MLlib library for greater flexibility and extensibility.
Uber AI Labs releases Atari Model Zoo, an open source repository of both trained Atari Learning Environment agents and tools to better understand them.
At an April 2019 meetup on ML and AI at Uber Seattle, members of our engineering team discussed three different approaches to enhancing our ML ecosystem.
Differentiable Plasticity is a new machine learning method for training neural networks to change their connection weights adaptively even after training is completed, allowing a form of learning inspired by the lifelong plasticity of biological brains.
Horovod, Uber's open source distributed deep learning system, enables NVIDIA to scale model training from one to eight GPUs for their self-driving sensing and perception technologies.
Ludwig version 0.2 integrates with Comet.ml, adds a new serving functionality, and incorporates the BERT text encoder, among other new features.
Zoubin Ghahramani, Head of Uber AI, discusses how we use artificial intelligence techniques to make our platform more efficient for users.
Curious about what it is like to traverse the high-dimensional loss landscapes of modern neural networks? Check out Uber AI Labs’ latest research on measuring intrinsic dimension to find out.