Aurora: A Foundation Model of the Atmosphere

no code implementations • 20 May 2024 • Cristian Bodnar, Wessel P. Bruinsma, Ana Lucic, Megan Stanley, Johannes Brandstetter, Patrick Garvan, Maik Riechert, Jonathan Weyn, Haiyu Dong, Anna Vaughan, Jayesh K. Gupta, Kit Tambiratnam, Alex Archibald, Elizabeth Heider, Max Welling, Richard E. Turner, Paris Perdikaris

Deep learning foundation models are revolutionizing many facets of science by leveraging vast amounts of data to learn general-purpose representations that can be adapted to tackle diverse downstream tasks.

Fast and Memory-Efficient Neural Code Completion

no code implementations • 28 Apr 2020 • Alexey Svyatkovskiy, Sebastian Lee, Anna Hadjitofi, Maik Riechert, Juliana Franco, Miltiadis Allamanis

Code completion is one of the most widely used features of modern integrated development environments (IDEs).

Code Completion Language Modelling +1

AMPNet: Asynchronous Model-Parallel Training for Dynamic Neural Networks

1 code implementation • ICLR 2018 • Alexander L. Gaunt, Matthew A. Johnson, Maik Riechert, Daniel Tarlow, Ryota Tomioka, Dimitrios Vytiniotis, Sam Webster

Through an implementation on multi-core CPUs, we show that AMP training converges to the same accuracy as conventional synchronous training algorithms in a similar number of epochs, but utilizes the available hardware more efficiently even for small minibatch sizes, resulting in significantly shorter overall training times.