Tag: Uber AI
Uber AI Labs proposes Loss Change Allocation (LCA), a new method that provides a rich window into the neural network training process.
We sat down with Jeff Clune, Senior Research Manager, to talk about his work in AI, journey to Uber, and Presidential Early Career Achievement in Science and Engineering (PECASE) award.
Zoubin Ghahramani, Head of Uber AI, discusses how we use artificial intelligence techniques to make our platform more efficient for users.
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.
The Plato Research Dialogue System enables experts and non-experts alike to quickly build, train, and deploy conversational AI agents.
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.
Uber builds upon the Lottery Ticket Hypothesis by proposing explanations behind these mechanisms and deriving a surprising by-product: the Supermask.
Created by Uber in 2017, Pyro was voted in by the Linux Foundation Deep Learning Technical Board as the latest incubation project to join its foundation.
We spoke with Fritz Obermeyer and Noah Goodman, Pyro project co-leads, about the potential of open source AI software at Uber and beyond.
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 developed Ludwig, a code-free deep learning toolbox, to make deep learning more accessible to non-experts and enable faster model iteration cycles.
Uber built Manifold, a model-agnostic visualization tool for ML performance diagnosis and model debugging, to facilitate a more informed and actionable model iteration process.
Uber AI Labs releases Atari Model Zoo, an open source repository of both trained Atari Learning Environment agents and tools to better understand them.
Metropolis-Hastings Generative Adversarial Networks (GANs) leverage the discriminator to pick better samples from the generator after ML model training is done.