Description
Reception and research poster presentations
-
Janina Hakenmรผller (Duke University)10/07/2023, 19:00Poster
The Accelerated AI Algorithms for Data-Driven Discovery (A3D3) Institute, funded by the National Science Foundation (NSF), under the Harnessing the Data Revolution (HDR) program, is a multi-disciplinary and geographically distributed entity with the primary mission to lead a paradigm shift in the application of real-time artificial intelligence (AI) at scale to advance scientific knowledge and...
Go to contribution page -
Alexander Joseph Schuy (University of Washington (US))10/07/2023, 19:00Poster
Given the recent advances of machine learning techniques, the Large Hadron Collider (LHC) at CERN is incorporating deep learning (DL) models, such as DeepCalo, to enhance the quality of data analysis of particle experiments. However, the need for in-time inference to keep up with data generation rates, as well as the dynamics of the experiments, require that the data processing feature short...
Go to contribution page -
Alexander Joseph Schuy (University of Washington (US))10/07/2023, 19:00Poster
In this study, we demonstrate the potential of sparse point-voxel convolutional neural networks (SPVCNN) for hadronic calorimetry tasks using HCAL and HGCAL datasets. By employing a modified object condensation loss, we train the network to group cell deposits into clusters while filtering out noise. We show that SPVCNN performs comparably to generic topological cluster-based methods in both...
Go to contribution page -
Dewen Zhong (Univ. Illinois at Urbana Champaign (US))10/07/2023, 19:00Poster
Efficient computational strategies are paramount for devices in resource-limited settings, particularly within high-energy physics experiments. To address this, we propose research primarily focused on improved energy efficiency and reduced latency inherent to AI algorithms implemented with analog circuits such as memristive crossbar arrays that perform in-memory matrix-vector multiply...
Go to contribution page -
Waiz Khan10/07/2023, 19:00Poster
High-level synthesis (HLS) offers the promise of simpler and easier hardware development, but at a cost. We consider the application of high-level synthesis to machine learning applications, seeking to quantify the resource and performance costs of this technique within the widely used HLS4ML framework. By creating carefully optimized SystemVerilog versions of identical HLS4ML designs, we...
Go to contribution page -
Abigail Gray10/07/2023, 19:00Poster
The current and upcoming Gravitational Wave (GW) observing runs by LIGO/Virgo/KAGRA detectors will result in significantly more detections than previous runs. Preparation to follow up associated electromagnetic signals promptly and accurately from binary neutron star (BNS) and neutron star black hole (NSBH) detections now depends heavily on real-time ML implementation at the detectors. The...
Go to contribution page -
Seungbin Park10/07/2023, 19:00Poster
Neural decoding is a critical task for understanding the function of the brain and providing solutions for neurological injury and disease. Two-photon calcium imaging has been a promising recording technique to observe a large population of neurons; however, decoding from two-photon calcium images is challenging because of the indirect and nonlinear representation of neural activity, low...
Go to contribution page -
Van Tha Bik Lian (Duke University)10/07/2023, 19:00Poster
We present a denoising autoencoder for extracting low-energy signals in Liquid Argon Time Projection Chamber (LArTPC) detectors. In particular, we are interested in neutrinos originating from core-collapse supernova events, and the detection of these neutrinos can help improve our knowledge of the physics of core-collapse supernova events [1]. Additionally, if we can detect them fast enough,...
Go to contribution page -
Josh Peterson10/07/2023, 19:00Poster
The IceCube Neutrino Observatory is a neutrino telescope located at the South Pole designed to detect Cherenkov radiation produced when neutrinos interact with the ice. It consists of 86 strings of digital optical modules, each containing a photomultiplier tube, embedded deep in the Antarctic ice. Each photon that encounters a photomultiplier tube produces a voltage waveform, and the photon...
Go to contribution page -
Benjamin Simon (Purdue University (US))10/07/2023, 19:00Poster
A graph neutral network (GNN) was constructed to identify charged lepton flavor violating decays of a tau particle into three muons in proton-proton collisions recorded with the CMS detector of the Large Hadron Collider. The muons from this decay are expected to have very low momentum, making them hard to detect in the high pileup environment expected at the high luminosity LHC (HL-LHC). We...
Go to contribution page -
Elham E Khoda (University of Washington (US))10/07/2023, 19:00Poster
Recent studies on the ITk data showed that the Graph Neural Network (GNN) -based track finding can provide not only satisfied track efficiency but also reasonable track resolutions. However, the GNN-based track finding is computationally slow in CPUs, demanding the usage of coprocessors like GPUs to speed up the inference time. The large graph size, normally 300k nodes and 1M edges,...
Go to contribution page -
Eric Anton Moreno (Massachusetts Institute of Technology (US))10/07/2023, 19:00Poster
Matched-filtering detection techniques for gravitational-wave (GW) signals in ground-based interferometers rely on having well-modeled templates of the GW emission.
Go to contribution page
However, interesting science cases aside from compact mergers do not yet have accurate enough modeling to make matched filtering possible, including core-collapse supernovae and other stochastic sources. Therefore the development... -
Jack Rodgers10/07/2023, 19:00Poster
In the Large Hadron Collider (LHC) at CERN, protons collide more than a million times per second. Pileup, which are interactions in the same or nearby proton bunch crossings in the accelerator, can be thought of as noise which affects many reconstructed physics variables such as the Jet Mass, Jet PT, and missing transverse momentum. This noise also results in worse resolution and as a...
Go to contribution page -
Andrew Skivington (University of California-San Diego, Duarte Lab)10/07/2023, 19:00Poster
At the LHC proton bunches are collided at a rate of 40MHz. The Compact Muon Superconducting Solenoid (CMS) detectorโs Level-1 (L1) trigger system is responsible for reducing this data rate to about 100kHz so that approximately 1% of these events can be saved for offline physics analyses. The task is to develop algorithms to determine what data to keep and what to discard. Traditionally,...
Go to contribution page -
Anthony Vizcaino Aportela (Univ. of California San Diego (US))10/07/2023, 19:00Poster
This poster presents an exploration into the realm of Beyond the Standard Model (BSM) Long-Lived Particles (LLPs) with a focus on the integration and development of a jet-tagging algorithm for the Compact Muon Solenoid (CMS) experiment's Level 1 (L1) Trigger system, in the context of the forthcoming upgrade to the High Luminosity Large Hadron Collider (HL-LHC). In spite of the challenges posed...
Go to contribution page -
YANG ZHENG10/07/2023, 19:00Poster
Recurrent Neural Networks (RNN) are ubiquitous computing systems for sequences and multivariate time series data. While several robust architectures of RNN are known, it is unclear how to relate RNN initialization, architecture, and other hyperparameters with accuracy for a given task. In this work, we propose to treat RNN as dynamical systems and to correlate hyperparameters with accuracy...
Go to contribution page -
Elham E Khoda (University of Washington (US)), Zhixing "Ethan" Jiang (University of Washington (US))10/07/2023, 19:00
During the next update of the High-Luminosity Large Hadron Collider (HL-LHC) of ATLAS, a new global trigger subsystem will be installed into the L0 Trigger. New and improved hardware and algorithms will be deployed during the upgrade to increase the performance of the trigger system. The global trigger subsystem consists of various components, including the FPGA-based Global Event Processor...
Go to contribution page -
Raghav Kansal (Univ. of California San Diego (US))10/07/2023, 19:00Poster
Fast, accurate detector simulations are necessary to keep up with the data collected in the coming years in HEP. Due to their stochastic nature, ML-based generative models are natural opportunities for fast, differentiable simulations. We present two such graph- and attention-based models for generating LHC-like data using sparse and efficient point cloud representations, with state-of-the-art...
Go to contribution page -
Dr Wei-Chen Wang (MIT)10/07/2023, 19:00Poster
Machine learning on tiny IoT devices based on microcontroller units (MCU) is appealing but challenging: the memory of microcontrollers is 2-3 orders of magnitude smaller even than mobile phones. We propose MCUNet, a framework that jointly designs the efficient neural architecture (TinyNAS) and the lightweight inference engine (TinyEngine), enabling ImageNet-scale inference on microcontrollers....
Go to contribution page -
Dr Wei-Chen Wang (MIT)10/07/2023, 19:00Poster
On-device training enables the model to adapt to new data collected from the sensors by fine-tuning a pre-trained model. However, the training memory consumption is prohibitive for IoT devices that have tiny memory resources. We propose an algorithm-system co-design framework to make on-device training possible with only 256KB of memory. On-device training faces two unique challenges: (1) the...
Go to contribution page -
JINGYUAN LI10/07/2023, 19:00Poster
Neural dynamical models reconstruct neural data using
Go to contribution page
dynamical systems. These models enable direct reconstruction and estimation of neural time-series data as well as estimation of neural latent states. Nonlinear neural dynamical models using recurrent neural networks in an encoder-decoder architecture have recently enabled accurate single-trial reconstructions of neural activity for... -
Desheng Ma10/07/2023, 19:00Poster
Electron ptychography enables deep sub-angstrom spatial resolution of atomic structures by solving the inverse problem of electron scattering through the sample, provided the complete distribution of transmitted electrons enabled by a new generation of detectors for scanning transmission electron microscopy (STEM). However, in practice, ptychographic reconstructions are computationally...
Go to contribution page -
Deep Chatterjee10/07/2023, 19:00
The observed events from the LIGO-Virgo-Kagra collaboration (LVK) have been modeled sources called compact binary coalescences (CBCs). Un-modeled transients, for example, from core-collapse supernovae or pulsar glitches remain undiscovered. In this work, we demonstrate the use of likelihood-free inference using normalizing flows for parameter estimation of un-modeled burst-type...
Go to contribution page -
Janina Hakenmรผller (Duke University)10/07/2023, 19:00Poster
The detection of a supernova burst is a unique opportunity to derive insights on astro and particle physics especially neutrinos. Neutrinos are the first hint of a supernova occuring to arrive on Earth due to their very low interaction cross section. They can provide extremely valuable information on the direction of burst enabling to point optical detection systems there in a multi messenger...
Go to contribution page -
Yichen Guo10/07/2023, 19:00Poster
Pulsed-laser deposition (PLD) is a powerful technique to grow complex oxides with controlled stoichiometry. To understand growth dynamics, it is common to leverage in situ spectroscopies such as reflection high energy electron diffraction (RHEED) to monitor surface crystallinity. Most commercial systems rely on video-rate cameras operating at 60-120 Hz that lack sufficient temporal resolution...
Go to contribution page -
Javier Mauricio Duarte (Univ. of California San Diego (US)), Michael Zhang10/07/2023, 19:00Poster
The particle-flow (PF) algorithm, which infers particles based on tracks and calorimeter clusters, is of central importance to event reconstruction in the CMS experiment at the CERN LHC, and has been a focus of development in light of planned Phase-2 running conditions with an increased pileup and detector granularity. In recent years, the machine learned particle-flow (MLPF) algorithm, a...
Go to contribution page -
Jialiang Zhang10/07/2023, 19:00Poster
HLS4ML is an influential Python package that creates firmware implementations of machine learning algorithms uses high-level synthesis (HLS) technique. While most of the templates are hand-written in HLS4ML, we want to further automate this manual design process by introducing PyLog, an algorithm-centric Python-based FPGA programming and synthesis flow, into the current HLS4ML flow and...
Go to contribution page -
Noah Paladino (Massachusetts Inst. of Technology (US))10/07/2023, 19:00Poster
The Particle Flow algorithm has proven highly effective in the offline reconstruction of events in the CMS detector. Combined with Pile-Up Per Particle Identification (PUPPI), the two algorithms provide the necessary basis for the construction of higher-level physics options, such as jets and taus. With the upcoming High Luminosity upgrade of the Large Hadron Collider (HL-LHC), implementing...
Go to contribution page -
Veronica Obute (Drexel University), Yael Passy10/07/2023, 19:00Poster
Increased development and utilization of multimodal scanning probe microscopy (SPM) and spectroscopy techniques have led to an orders-of-magnitude increase in the volume, velocity, and variety of collected data. While larger datasets have certain advantages, practical challenges arise from their increased complexity including the extraction and analysis of actionable scientific information. In...
Go to contribution page -
Ethan Marx (MIT)10/07/2023, 19:00Poster
As the global network of gravitational wave detectors grows in both size and sensitivity, the traditional matched filtering method for detecting signals from compact object mergers becomes computationally prohibitive. Machine learning algorithms are a compelling alternative approach to this problem due to their ability to shift the computational cost to the model training process, enabling...
Go to contribution page -
Zihan Zhao (Univ. of California San Diego (US))10/07/2023, 19:00Poster
Limited by the lack of truth labels on real data, fully supervised ML algorithms are constrained to training only with simulated samples. With self-supervised learning, we can leverage vast amounts of unlabeled real data to facilitate training. We investigate the application of [VICReg][1], a contrastive learning model, on a classification task: discriminating signal jets (e.g. $H \rightarrow...
Go to contribution page -
Xiaohan Liu10/07/2023, 19:00Poster
A specific type of Electroencephalography (EEG) signals, sleep spindle, is believed to contribute to neuronal plasticity and memory consolidation. In this project, we proposed a system that is based on ultra-low latency and power FPGA to detect and interact with the sleep spindles to further understand the mechanism behind the theory. The proposed system will have a programmed FPGA that...
Go to contribution page -
Arif Chu (University of Washington Seattle)10/07/2023, 19:00Poster
Spectrograms are frequently used to provide qualitative insights into the types of noise and signals present in audio data. Similarly, we can use them to gain insights from data such as real gravitational wave from gravitational wave detectors. Simply by eye, we can see characteristic chirp signals from gravitational waves due to the physics of the black holes' inspiral. Designing a novel...
Go to contribution page -
Trung Le10/07/2023, 19:00Poster
Modeling neural population dynamics underlying noisy single-trial spiking activities is essential for relating neural observation and behavior. A recent non-recurrent method - Neural Data Transformers (NDT) - has shown great success in capturing neural dynamics with low inference latency without an explicit dynamical model. However, NDT focuses on modeling the temporal evolution of the...
Go to contribution page -
Shikun Liu10/07/2023, 19:00
In many real-world applications, graph-structured data used for training and testing have differences in distribution, such as in high energy physics (HEP) where simulation data used for training may not match real experiments. Graph domain adaptation (GDA) is a method used to address these differences. However, current GDA primarily works by aligning the distributions of node representations...
Go to contribution page -
Xinqiao Zhang10/07/2023, 19:00Poster
Ferroelectrics, characterized by spontaneous polarization and reversible switching, play a crucial role in various applications such as non-volatile FeRAM, ferro-TFET, and catalysis. However, the influence of environmental factors on ferroelectric domain dynamics remains poorly characterized. This work aims to investigate the impact of temperature and background gas on the domain mapping of...
Go to contribution page -
Joshua Queen10/07/2023, 19:00Poster
The Deep Underground Neutrino Experiment (DUNE), a 40 kt fiducial mass liquid argon time projection chamber (LArTPC), will be unique among supernova (SN) neutrino detectors due to its ability to measure the electron neutrino flavor component of a SN burst. Crucial to achieving a good pointing resolution is the ability to discriminate the directionality of primary electron tracks via a process...
Go to contribution page -
Mr Daniel G Fredin (University of Washington), Mr Cole Welch (University of Washington)10/07/2023, 19:00Poster
The Laser Interferometer Gravitational Wave-Observatory (LIGO) has accumulated more than 4.5 petabytes (Pb) of data in its quest to detect gravitational waves. Furthermore, it is anticipated that the total data accrued will increase by approximately 0.8 petabytes per year. The processing and analysis of the extensive volume of data from LIGO necessitates a tremendous amount of computational...
Go to contribution page -
Lauren Peterson (University of Washington)10/07/2023, 19:00Poster
Brain-computer interfaces use the electrical activity of the brain to control an external device, but decoding complex neural signals requires large amounts of computational power and time. We use a novel convex optimization algorithm to do real-time feature selection based on relevance, sparsity, and smoothness. We demonstrate that the algorithm can reduce the feature set while maintaining...
Go to contribution page -
Simon Rothman (Massachusetts Inst. of Technology (US))Poster
The Compact Muon Solenoid (CMS) detector is one of two general-purpose detectors at
Go to contribution page
the CERN LHC. Products of proton-proton collisions at a center of mass energy of 13 TeV are reconstructed in the CMS detector to probe the standard model of particle physics and to search for processes beyond the standard model. The development
of precision algorithms for this reconstruction is therefore a...