[hpc-announce] Call to participate: (Virtual) April Monterey Data Workshop 2022 - Convergence of HPC & AI (April 20-21)

[Hai Ah Nam]

REGISTER to attend the
April Monterey Data Workshop 2022 - Convergence of HPC & AI
AGENDA:  https://www.montereydataconference.org/workshop-2022
APRIL 20-21, 2022 | VIRTUAL ONLY
----------------------------------------------------------------------------
REGISTRATION: https://forms.gle/AwwHtnjvkX6vCuU76 (free registration)

We are pleased to announce the 1st DOE Monterey Data Workshop 2022 to
share the latest research in scientific artificial intelligence (AI)
and Machine Learning (ML) in preparation for the Fall 2022 Monterey
Data Conference.

The Monterey Data Workshop brings together researchers from DOE
national laboratories, facilities, universities, and industry to share
research in scientific artificial intelligence (AI) and Machine
Learning (ML).

The workshop is designed to promote discussion and feedback. We plan
to have a combination of technical talks and lively panel sessions.

Agenda includes:
==================================================================
WEDNESDAY, April 20, Technical Sessions
==================================================================
** Session 1a - AI Methods & Applications - Chair: Talita Perciano Costa Leite
Aditi Krishnapriyan, Lawrence Berkeley National Laboratory
Integrating machine learning with scientific spatial and temporal modeling

Yifei Guan, Rice University
Physics-constrained convolutional neural networks in the small-data
regime for large-eddy simulation of fluid turbulence

Amir Gholami, Shashank Subramanian, UC Berkeley
Rethinking Physics Informed Neural Networks

Banafsheh Rekabdar, Portland State University
Biologically Inspired Variational Auto-Encoders for Adversarial Robustness

** Session 1b - AI Methods & Applications - Chair: Peter Zwart
Ashesh Chattopadhyay, Rice University
Deep Learning Meets Data Assimilation: On Physically-consistent
Architectures and Hybrid Ensemble Kalman Filters for Weather
Forecasting

Talita Perciano, Lawrence Berkeley National Laboratory
Learning with Multidimensional and Multiscale Scientific Data

Alice Gatti, Lawrence Berkeley National Laboratory
Deep learning for graph partitioning

Dario DemattiesNorthwestern Argonne Institute of Science and
Engineering (NAISE)Let's unleash the network judgement: A
self-supervised approach for Cloud Image Segmentation
Panel Discussion - Moderator: Aditi Krishnapriyan

** Session 2 - AI for self-driving scientific facilities- Chair: Hai Ah Nam
Brian Sammuli, General Atomics
Recent Machine Learning Developments at the DIII-D National Fusion Facility

Mariam Kiran, Lawrence Berkeley National Laboratory
AI engine designed for high performance network engineering

Marcus Noack, Lawrence Berkeley National Laboratory
Gaussian-Process-Driven Optimal Autonomous Data Acquisition for
Large-Scale Experimental Facilities

John Wright, MIT
ACCELERATING RADIO FREQUENCY HEATING MODELS for FUSION USING MACHINE LEARNING
Panel Discussion - Moderator: Kevin Yager, BNL

**POSTER
Ellianna Abrahams, UC Berkeley
The Curly U-Net: A Physics-Featurized U-Net to Denoise Temporal Image
Cubes with Time-Averaged Point-Mass Measurements

==================================================================
THURSDAY, April 21, Technical Sessions
==================================================================
** Session 3a - Scalable & Productive Computing Systems for AI -
Chair: Wahid Bhimji
Pawel Gepner, Graphcore
AI MEETS HPC IN SCIENTIFIC COMPUTING USING GRAPHCORE IPUS

Sean Peisert, Berkeley Lab
Edge-to-Center Data Enclaves for Scientific Computing

Cindy Orozco-Bohorquez, Cerebras Systems
AI experimentation with 850,000 cores

Amit Majumdar, San Diego Supercomputer Center, University of
California San Diego
Voyager - a Habana Gaudi Training and Goya Inference processor based
scalable AI Machine for the science and engineering community

Panel Discussion - Scalable & Productive Computing System - Moderator:
Wahid Bhimji, LBNL

** Session 3b - Scalable & Productive Computing Systems for AI -
Chair: Steve Farrell
Zhen Xie, Argonne National Laboratory
Throughput-oriented and Accuracy-aware DNN Training with BFloat16 on GPU

Junqi Yin, Oak Ridge National Laboratory
Integrating AI with HPC Simulations

Eric Roberts, Lawrence Berkeley National Lab
CAMERA & MBIBBuilding customizable deep learning solutions using pyMSDtorch

Panel Discussion / Q&A - Moderator - Steve Farrell

** Session 4 - AI and Data Management - Chair: Suren Byna
Martin Foltin, HPE
Self-learning Data Foundation for Scientific AI

Tristan Vanderbruggen, Lawrence Livermore National Laboratory
HPCFAIR: An Infrastructure for FAIR AI and Scientific Datasets for HPC
Applications

Rangan Sukumar, Kristyn Maschhoff, HPE
A Scientific Datastore with AI Search built on HPC-first principles
Panel Discussion - AI & Data - Moderator: Suren Byna