Fast Machine Learning for Science Conference 2024

from Tuesday, October 15, 2024 (8:00 AM) to Friday, October 18, 2024 (9:00 PM)
Purdue University (Steward Center 306 (Third floor))

        : Sessions
    /     : Talks
        : Breaks
Oct 15, 2024
Oct 16, 2024
Oct 17, 2024
Oct 18, 2024
AM
8:15 AM --- Registration ---
9:00 AM Welcome  
9:10 AM
Invited talks (until 10:55 AM)
9:10 AM [Remote] Opening Talk - Javier Mauricio Duarte (Univ. of California San Diego (US))  
9:45 AM Fast Machine Learning at the LHC - Dylan Sheldon Rankin (University of Pennsylvania (US))  
10:20 AM Enabling real-time detection, characterization and inference for the time-domain sky - Gautham Narayan (UIUC)  
10:55 AM
Coffee/Posters (until 11:20 AM)
11:20 AM
Invited talks (until 1:05 PM)
11:20 AM [Remote] Machine learning and electronic structure calculation in materials and beyond - Kieron Burke  
11:55 AM ML for Accelerator control and design - Daniel Ratner (SLAC)  
12:30 PM Topological diagnostics of ML and AI algorithms - David Gleich (Purdue)  
9:00 AM
Invited talks (until 10:45 AM)
9:00 AM (fast) Machine Learning Applications for Neuroscience - Jai Yu (U Chicago)  
9:35 AM [Remote] Efficient Deep Learning with Sparsity - Zhijian Liu (UCSD)  
10:10 AM AI’s Energy Challenge and four A’s to address it - Anand Raghunathan (Purdue University)  
10:45 AM
Coffee/Posters (until 11:10 AM)
11:10 AM
Invited talks (until 12:20 PM)
11:10 AM Deep Learning Complexity in Neuromorphic Quantum Materials - Erica Carlson  
11:45 AM [Remote] P-bits (quantum-inspired probabilistic computing) - Supriyo Datta (Purdue University)  
9:00 AM
Invited talks (until 10:45 AM)
9:00 AM Agile Hardware Development: Architecture and Tools - Callie Hao  
9:35 AM LLMs for chip design - Siddharth Garg  
10:10 AM Industry talk: AMD - Abhishek Jain  
10:45 AM
Coffee/Posters (until 11:10 AM)
11:10 AM
Invited talks (until 12:20 PM)
11:10 AM AI and ML at the future Electron Ion Collider - Cristiano Fanelli (William & Mary)  
11:45 AM Real-time ML-FPGA filter for particle identification and tracking in nuclear physics - Sergey Furletov (Jefferson lab)  
9:00 AM
HLS4ML tutorial - Jan-Frederik Schulte (Purdue University (US)) (until 11:00 AM)
9:00 AM
SONIC tutorial - Yuan-Tang Chou (University of Washington (US)) (until 10:00 AM) (BHEE 234)
10:00 AM
ECE Distinguished Lecture: Optics à la mode – a new way of making, using and understanding optics (until 11:00 AM)
10:00 AM
Next Generation Triggers (until 12:00 PM)
10:00 AM NGT From CMS (L1 Trigger) - Jennifer Ngadiuba (FNAL)  
10:20 AM NGT From CMS(HLT) - Marco Rovere (CERN)  
10:40 AM NGT From ATLAS - Markus Elsing (CERN)  
11:20 AM Discussion  
10:00 AM SONIC developer meeting - Yuan-Tang Chou (University of Washington (US)) (until 11:00 AM) (BHEE 234)
11:00 AM
HDR ML challenge hand-on session - Yuan-Tang Chou (University of Washington (US)) (until 12:00 PM) (Room 105, Lambert Fieldhouse)
PM
1:05 PM --- Lunch ---
2:00 PM
Contributed talks (until 3:15 PM)
2:00 PM [Remote] Randomized Point Serialization-Based Efficient Point Transformer in High-Energy Physics Applications - Siqi Miao (Georgia Tech)  
2:15 PM A Streamlined Neural Model for Real-Time Analysis at the First Level of the LHCb Trigger - Jiahui Zhuo (Univ. of Valencia and CSIC (ES))  
2:30 PM ML4GW: An all-encompassing software framework for real-time deep learning applications to search for gravitational waves - Will Benoit  
2:45 PM SONIC: A Portable framework for as-a-service ML serving - Dmitry Kondratyev (Purdue University (US))  
3:00 PM Deep(er)RICH: Reconstruction of Imaging CherenkovDetectors with Swin Transformers and Normalizing Flow Models - James Giroux (W&M)  
3:15 PM
Lighting talks (until 4:25 PM)
3:15 PM Robust and interpretable deep learning by leveraging domain knowledge - Mirco Hünnefeld (University of Wisconsin-Madison)  
3:20 PM Intelligent experiments through real-time AI: GNN-based trigger pipeline for sPHENIX - Jovan Mitrevski (Fermi National Accelerator Lab. (US))  
3:25 PM Interpreting and Accelerating Transformers for Jet Tagging - Aaron Wang (University of Illinois at Chicago (US)) Vivekanand Gyanchand Sahu (University of California San Diego)  
3:30 PM S-QUARK: A Scalable Quantization-Aware Training Framework for FPGA Deployment based on Keras-v3 - Chang Sun (California Institute of Technology (US))  
3:35 PM Online track reconstruction with graph neural networks on FPGAs for the ATLAS experiment - Jared Burleson (University of Illinois at Urbana-Champaign)  
3:40 PM IceSONIC - Network AI Inference on Coprocessors for IceCube Offline Processing - Benedikt Riedel  
3:45 PM Towards Online Machine Learning in DUNE Data Acquisition - Andrew Mogan  
3:50 PM Fast Simulation of Particle Physics Calorimeters - Oz Amram (Fermi National Accelerator Lab. (US))  
3:55 PM Real-Time AI-Based Data Selection in LArTPC Experiments Using Accelerated FPGA Platforms - Akshay Malige  
4:00 PM Benchmarking and Interpreting Real-Time Quench Detection Algorithms - Maira Khan (Fermi National Accelerator Laboratory)  
4:05 PM Real-time Reinforcement Learning on AI Engines with Online Training for Autonomous Accelerators - Luca Scomparin  
4:10 PM AI Red Teaming for Science - Anita Nikolich (UIUC)  
4:15 PM An Efficient Multiply Accumulate Tree for Real-time Quantized Neural Networks - Chang Sun (California Institute of Technology (US))  
4:20 PM A gradient-based hardware-aware neural architecture search framework for hls4ml - ChiJui Chen  
4:25 PM
Coffee/Posters (until 5:00 PM)
5:00 PM
Contributed talks (until 6:25 PM)
5:00 PM [Remote] Visualizing Loss Landscapes for Scientific Edge Machine Learning - Caleb Geniesse (Lawrence Berkeley National Laboratory)  
5:15 PM GWAK: Low-Latency Machine Learning for Real-Time Detection of Unmodeled Gravitational Wave Transients - Eric Anton Moreno (Massachusetts Institute of Technology (US))  
5:30 PM Realtime Anomaly Detection in the CMS Experiment - Noah Alexander Zipper (University of Colorado Boulder (US))  
5:45 PM Active Machine Learning for Projection Multi-photon 3D Printing - Mr Jason Edward Johnson (Purdue University)  
6:00 PM [Remote] Rapid, High-Resolution Coherent Diffractive Imaging with Physics-Informed Machine Learning - Oliver Hoidn  
6:30 PM --- Reception ---
12:20 PM
Contributed talks (until 12:45 PM)
12:45 PM --- Lunch ---
2:00 PM
Invited talks (until 3:10 PM)
2:00 PM Tools, Methodologies, and Co-design Principles for Building Microelectronics Artifacts for ML - Seda Ogrenci (Northwestern University)  
2:35 PM [Remote] ML for material science - Sergei Kalilin  
3:10 PM
Lighting talks (until 4:15 PM)
3:10 PM Model-Independent Real-Time Anomaly Detection at CMS with CICADA - Lino Oscar Gerlach (Princeton University (US))  
3:15 PM Unsupervised Learning Methods of Real-Time Anomaly Detection for Data Selection and Detector Monitoring in Liquid Argon Time Projection Chambers - Jack Henry Cleeve (Columbia University)  
3:20 PM An open platform for in-situ high-speed computer vision with hls4ml - Ryan Forelli (Northwestern University)  
3:25 PM PearNets for Pearson Correlated Latent Optimization of Nanophotonic Devices - Michael Tan Bezick  
3:30 PM EnsembleLUT: Scaling up LUT-based Neural Networks with Ensemble Learning - Olivia Weng  
3:35 PM An Efficient and Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks - Hoin Jung (Purdue University)  
3:40 PM wa-hls4ml: A benchmark and dataset for ML accelerator resource estimation - Ben Hawks (Fermi National Accelerator Lab)  
3:45 PM Neural Architecture Codesign for Fast Physics Applications - Dmitri Demler  
3:50 PM Comprehensive Analysis of UNet Variants in Cardiac Image Segmentation - Niharika Das (G H Raisoni University)  
3:55 PM Edge SpAIce: Enabling On-Board Data Compression With Machine Learning On FPGAs - Nicolò Ghielmetti (CERN)  
4:15 PM
Coffee/Posters (until 4:45 PM)
4:45 PM
Contributed talks (until 6:20 PM)
4:45 PM Fast Data, Faster Science: Connecting Instruments to Real-Time AI Compute - Denis Leshchev  
5:00 PM An end-to-end ML-enabled platform for precision neuroscience - Emadeldeen Hamdan (University of Illinois Chicago)  
5:15 PM Artificial Brains for Artificial Intelligence: A Novel Neurophysically Inspired Neural Network - Lorenzo Cacciapuoti  
5:30 PM Smart Pixels: Towards radiation hard ASIC with on-chip machine learning in 28nm CMOS - Ms Jieun Yoo (UIC)  
5:45 PM Bit-Width Optimization of Power-Efficient Hardware Accelerators for Neural Networks using Catapult AI NN - Marzieh Vaez Torshizi (Siemens EDA)  
6:00 PM End-to-end workflow for ML-based qubit readout with QICK + hls4ml - Botao Du (Purdue University)  
12:20 PM --- Lunch ---
1:10 PM
Contributed talks (until 3:20 PM)
1:10 PM rule4ml: An Open-Source Tool for Resource Utilization and Latency Estimation for ML Models on FPGA - Hamza Ezzaoui Rahali (University of Sherbrooke)  
1:25 PM Large Neural Network Partitionning for Distributed Inference on FPGAs - Charles-Étienne Granger (Université de Sherbrooke)  
1:40 PM Accelerating Reproducible FPGA Machine Learning Research With a Workflow Management Framework - Alexis Shuping (Northwestern University)  
1:55 PM Differentiable Weightless Neural Networks - Alan T. L. Bacellar (University of Texas at Austin)  
2:10 PM [Remote] Machine Learning Inference on FPGAs Using HLS4ML with oneAPI Backend - Haoyan Wang (Intel Corporation)  
2:30 PM [Remote] BRAM-Aware Quantization for Efficient Transformer Inference via Tile-based Architecture on a FPGA - Ling-Chi Yang (Institute of Electronics in National Yang Ming Chiao Tung University)  
2:45 PM Episodic reinforcement learning for 0νββ decay signal discrimination - Sonata Simonaitis-boyd  
3:00 PM Towards a machine learning trigger for high-purity germanium spectrometers - Janina Dorin Hakenmueller (Duke University)  
3:20 PM
Coffee/Posters (until 3:30 PM)
3:30 PM Physics Colloquium [No remote participation] - Philip Coleman Harris (Massachusetts Inst. of Technology (US))   (PHYS 112)
5:00 PM HLS4ML developer's meeting   (PHYS 390)
6:30 PM --- Conference Dinner ---
12:00 PM --- lunch ---
1:45 PM
Awards and Closeout (until 2:30 PM)
1:45 PM Poster awards  
1:50 PM Closeout talk - Sasha Boltasseva (Purdue University)  
3:00 PM
Fast ML not-for-profit chat (until 5:00 PM) (390)