Schedule
8:30-8:40: Opening Remarks, Aparna Lakshmiratan, Facebook AI
Session 1, Chair: Aparna Lakshmiratan, Facebook AI
8:40 - 9:10 Keynote 1: Machine Learning Reproducibility: An update from the NeurIPS 2019 Reproducibility Co-Chairs, Joelle Pineau, McGill University and Facebook
9:10 - 9:30 Contributed Talk: SLIDE : Training Deep Neural Networks with Large Outputs on a CPU faster than a V100-GPU
9:30 - 9:50 Contributed Talk: NeMo: A Toolkit for Building AI Applications Using Neural Modules
Morning Poster Session, Chair: Sid Sen, Microsoft Research
9:50 - 10:00: Poster Overview
10:00 - 11:10 Break and Poster Session
Session 2: Chair: Sid Sen, Microsoft Research
11:10 - 11:40 Keynote 2: Balancing Efficiency and Flexibility for DNN Acceleration, Vivienne Sze, MIT
11:40 - 12:00 Contributed Talk: 5 Parallel Prism: A Topology for Pipelined Implementations of Convolutional Neural Networks Using Computational Memory
12:00 - 1:30 Lunch
Systems Bonanza, Chair: Dan Crankshaw, Microsoft Research
1:30 - 3:30 Systems Bonanza (10 minutes each)
- PyTorch (Dmytro Dzhulgakov, Facebook)
- TensorFlow (Jonathan Hseu, Google Brain)
- Keras (Yifei Feng, Google Brain)
- TVM (Tianqi Chen, OctoML)
- Ray (Robert Nishihara, UC Berkeley)
- ONNX Runtime (Faith Xu, Microsoft)
- CoreML (Reza Farhadi, Apple)
- Flux (Shashi Gowda, MIT)
- MLFlow (Matei Zaharia, Stanford University and Databricks)
- MLPerf (Peter Mattson, Google Brain)
- Microsoft RL Systems (Paul Mineiro, Microsoft Research)
- MXNet (Alex Smola, Amazon Web Services)
Afternoon Poster Session
3:30 - 4:30 Break and Poster Session
Session 3, Chair: Sarah Bird, Microsoft Research
4:30 - 5:00 Keynote 3: Programming the Graphcore IPU, Ryota Tomioka, Microsoft Research
5:00 - 5:20 Contributed Talk: LISA: Towards Learned DNA Sequence Search
5:20 - 5:30 Closing Remarks