BNL AI/ML Working Group Seminar Series
from
Tuesday 14 September 2021 (12:00)
to
Tuesday 1 March 2022 (17:00)
Monday 13 September 2021
Tuesday 14 September 2021
12:00
Keeping the human in the loop: autopilot for experiments at diffraction beamlines
-
Phillip Maffettone
Keeping the human in the loop: autopilot for experiments at diffraction beamlines
Phillip Maffettone
12:00 - 13:00
References: https://www.nature.com/articles/s43588-021-00059-2 https://www.nature.com/articles/s41524-021-00575-9 https://iopscience.iop.org/article/10.1088/2632-2153/abc9fc https://arxiv.org/abs/2104.00864
Wednesday 15 September 2021
Thursday 16 September 2021
Friday 17 September 2021
Saturday 18 September 2021
Sunday 19 September 2021
Monday 20 September 2021
Tuesday 21 September 2021
Wednesday 22 September 2021
Thursday 23 September 2021
Friday 24 September 2021
Saturday 25 September 2021
Sunday 26 September 2021
Monday 27 September 2021
Tuesday 28 September 2021
Wednesday 29 September 2021
Thursday 30 September 2021
Friday 1 October 2021
Saturday 2 October 2021
Sunday 3 October 2021
Monday 4 October 2021
Tuesday 5 October 2021
Wednesday 6 October 2021
Thursday 7 October 2021
Friday 8 October 2021
Saturday 9 October 2021
Sunday 10 October 2021
Monday 11 October 2021
Tuesday 12 October 2021
Wednesday 13 October 2021
Thursday 14 October 2021
Friday 15 October 2021
Saturday 16 October 2021
Sunday 17 October 2021
Monday 18 October 2021
Tuesday 19 October 2021
Wednesday 20 October 2021
Thursday 21 October 2021
Friday 22 October 2021
Saturday 23 October 2021
Sunday 24 October 2021
Monday 25 October 2021
Tuesday 26 October 2021
Wednesday 27 October 2021
Thursday 28 October 2021
Friday 29 October 2021
Saturday 30 October 2021
Sunday 31 October 2021
Monday 1 November 2021
Tuesday 2 November 2021
12:00
Provably exact sampling for first-principles theoretical physics
-
Phiala Shanahan
(
MIT
)
Provably exact sampling for first-principles theoretical physics
Phiala Shanahan
(
MIT
)
12:00 - 13:00
Abstract: In the context of lattice quantum field theory calculations in particle and nuclear physics, I will describe avenues to accelerate sampling from known probability distributions using machine learning. I will focus in particular on flow-based generative models, and describe how guarantees of exactness and the incorporation of complex symmetries (e.g., gauge symmetry) into model architectures can be achieved. I will show the results of proof-of-principle studies that demonstrate that sampling from generative models can be orders of magnitude more efficient than traditional Hamiltonian/hybrid Monte Carlo approaches in this context. Biography: Phiala Shanahan obtained her BSc and PhD from the University of Adelaide in 2012 and 2015. Before joining the MIT physics faculty in 2018, Prof. Shanahan was a Postdoctoral Associate at MIT and held a joint position as Assistant Professor at the College of William & Mary and Senior Staff Scientist at the Thomas Jefferson National Accelerator Facility. Prof. Shanahan is the recipient of Early-Career Awards from both the NSF and the DOE, and in 2021 was awarded the Maria Goeppert Mayer Award of the American Physical Society.
Wednesday 3 November 2021
Thursday 4 November 2021
Friday 5 November 2021
Saturday 6 November 2021
Sunday 7 November 2021
Monday 8 November 2021
Tuesday 9 November 2021
Wednesday 10 November 2021
Thursday 11 November 2021
Friday 12 November 2021
Saturday 13 November 2021
Sunday 14 November 2021
Monday 15 November 2021
Tuesday 16 November 2021
Wednesday 17 November 2021
Thursday 18 November 2021
Friday 19 November 2021
Saturday 20 November 2021
Sunday 21 November 2021
Monday 22 November 2021
Tuesday 23 November 2021
Wednesday 24 November 2021
Thursday 25 November 2021
Friday 26 November 2021
Saturday 27 November 2021
Sunday 28 November 2021
Monday 29 November 2021
Tuesday 30 November 2021
Wednesday 1 December 2021
Thursday 2 December 2021
Friday 3 December 2021
Saturday 4 December 2021
Sunday 5 December 2021
Monday 6 December 2021
Tuesday 7 December 2021
Wednesday 8 December 2021
Thursday 9 December 2021
Friday 10 December 2021
Saturday 11 December 2021
Sunday 12 December 2021
Monday 13 December 2021
Tuesday 14 December 2021
Wednesday 15 December 2021
Thursday 16 December 2021
Friday 17 December 2021
Saturday 18 December 2021
Sunday 19 December 2021
Monday 20 December 2021
Tuesday 21 December 2021
Wednesday 22 December 2021
Thursday 23 December 2021
Friday 24 December 2021
Saturday 25 December 2021
Sunday 26 December 2021
Monday 27 December 2021
Tuesday 28 December 2021
Wednesday 29 December 2021
Thursday 30 December 2021
Friday 31 December 2021
Saturday 1 January 2022
Sunday 2 January 2022
Monday 3 January 2022
Tuesday 4 January 2022
Wednesday 5 January 2022
Thursday 6 January 2022
Friday 7 January 2022
Saturday 8 January 2022
Sunday 9 January 2022
Monday 10 January 2022
Tuesday 11 January 2022
Wednesday 12 January 2022
Thursday 13 January 2022
Friday 14 January 2022
Saturday 15 January 2022
Sunday 16 January 2022
Monday 17 January 2022
Tuesday 18 January 2022
Wednesday 19 January 2022
Thursday 20 January 2022
Friday 21 January 2022
Saturday 22 January 2022
Sunday 23 January 2022
Monday 24 January 2022
Tuesday 25 January 2022
Wednesday 26 January 2022
Thursday 27 January 2022
Friday 28 January 2022
Saturday 29 January 2022
Sunday 30 January 2022
Monday 31 January 2022
Tuesday 1 February 2022
12:00
High Performance FPGA Embedded System for Machine Learning Based Tracking and Trigger in sPhenix and EIC
-
Dantong Yu
(
New Jersey Institute of Technology
)
High Performance FPGA Embedded System for Machine Learning Based Tracking and Trigger in sPhenix and EIC
Dantong Yu
(
New Jersey Institute of Technology
)
12:00 - 13:00
We present a comprehensive end-to-end pipeline to classify triggers versus background events in this paper. This pipeline makes online decisions to select signal data and enables the intelligent trigger system for efficient data collection in the Data Acquisition System (DAQ) of the upcoming sPHENIX and future EIC (Electron-Ion Collider) experiments. Starting from the coordinates of pixel hits that are lightened by passing particles in the detector, the pipeline applies three-stages of event processing (hits clustering, track reconstruction, and trigger detection) and labels all processed events with the binary tag of trigger versus background events. The pipeline consists of deterministic algorithms such as clustering pixels to reduce event size, tracking reconstruction to predict candidate edges, and advanced graph neural network-based models for recognizing the entire jet pattern. In particular, we apply the Message-Passing Graph Neural Network to predict links between hits and reconstruct tracks and a hierarchical pooling algorithm (DiffPool) to make the graph-level trigger detection. We obtain an impressive performance (>= 70% accuracy) for trigger detection with only 3200 neuron weights in the end-to-end pipeline. We deploy the end-to-end pipeline into a field-programmable gate array (FPGA) and accelerate the three stages with speedup factors of 1152, 280, and 21, respectively. Biography: Dantong Yu received a BS degree in computer science from Peking University and a Ph.D. degree in Computer Science from University at Buffalo. He joined Martin Tuchman School of Management at the New Jersey Institute of Technology in 2016. Before that, he worked for Brookhaven National Laboratory for sixteen years and collaborated with Physicists on multiple experiments, including ATLAS, STAR, and PHENIX. He founded and led the Computer Science Group in BNL between 2009 and 2016. His research interests include data mining, machine learning, high-speed network, and communication protocols. He has published 70 papers in leading technical journals and conferences. He has served on the review panels for NSF, DOE Early Career Investigator, and DOE SBIR/STTR. He is a PC member of KDD, ICDM, CIKM, ICDE, ICCCN, HiPC, and ICPADS.
Wednesday 2 February 2022
Thursday 3 February 2022
Friday 4 February 2022
Saturday 5 February 2022
Sunday 6 February 2022
Monday 7 February 2022
Tuesday 8 February 2022
Wednesday 9 February 2022
Thursday 10 February 2022
Friday 11 February 2022
Saturday 12 February 2022
Sunday 13 February 2022
Monday 14 February 2022
Tuesday 15 February 2022
Wednesday 16 February 2022
Thursday 17 February 2022
Friday 18 February 2022
Saturday 19 February 2022
Sunday 20 February 2022
Monday 21 February 2022
Tuesday 22 February 2022
Wednesday 23 February 2022
Thursday 24 February 2022
Friday 25 February 2022
Saturday 26 February 2022
Sunday 27 February 2022
Monday 28 February 2022
Tuesday 1 March 2022
12:00
When reinforcement learning meets quantum computing
-
Yen-Chi (Sam) Chen
(
Brookhaven National Laboratory
)
When reinforcement learning meets quantum computing
Yen-Chi (Sam) Chen
(
Brookhaven National Laboratory
)
12:00 - 13:00
Recently, reinforcement learning (RL) has demonstrated various applications with superhuman performance such as mastering the game of Go. Meanwhile, the development of quantum computing hardware shed light on building practical quantum applications to tackle previously unsolved problems. What will happen if we combine these two fascinating techniques? In this talk, I will present the recent progress in quantum RL as well as using classical RL to help certain tasks in quantum computing.