Over the past decade, machine learning algorithms have been deployed in many cloud-centric applications. However, as the application space continues to grow, various algorithms are now embedded “closer to the sensor,” eliminating the latency, privacy and energy penalties associated with cloud access. In this talk, I will review circuit techniques that can improve the energy efficiency of...
We present a new approach for positron emission tomography (PET) event classification that integrates machine learning with quantum-aware signal processing. Our system utilizes a cross-strip Cadmium Zinc Telluride (CZT) detector architecture optimized for high-resolution spatial and energy discrimination. By exploiting quantum correlations of annihilation photons, we aim to enhance the...
Advancements in High Energy Physics (HEP) increasingly rely on intelligent instrumentation capable of processing vast, complex datasets in real time. As detectors evolve, front-end electronics must not only manage extreme data rates with minimal latency and power consumption but also withstand harsh environmental conditions, such as high radiation and cryogenics. Traditional...
We present our ongoing work toward developing machine learning (ML) algorithms for embedded Field-Programmable Gate Arrays (eFPGAs) integrated on readout Application-Specific Integrated Circuits (ASICs). Our focus is on reconfigurable Pulse-Shape Discrimination (PSD), a critical signal processing technique for neutron imaging and other imaging modalities. By leveraging the reconfigurability of...
The SLAC Neural Network Library (SNL) is a high-performance, hardware-aware framework for deploying machine learning models on FPGAs at the edge of the scientific data chain. Developed using Xilinx's High-Level Synthesis (HLS) tools, SNL combines the flexibility of software-defined design with the low-latency, high-throughput advantages of reconfigurable hardware. It offers a user-friendly API...
cgra4ml is a highly flexible, high-performance accelerator system that helps researchers build, train, and implement machine learning models on Field Programmable Gate Arrays (FPGAs). It extends the capabilities of HLS4ML by allowing off-chip data storage and supporting a broader range of neural network architectures, including models like ResNet and PointNet. Using this new framework, we...
Belle II is the second-generation $B$ physics experiment located at the SuperKEKB asymmetric $e^+ e^−$ collider, operating at the $\Upsilon(4S)$ resonance. The $\tau$ physics program at Belle II involves both probes of new physics and precision measurements of SM parameters with large statistics. These include placing strong constraints on lepton flavor violation [1], probing CP violation in...
Many physics analyses use some form of AI/ML to identify physics objects such as jets and electrons and/or for whole event classification. However, such an approach has generally been taken a long time after the detector was designed and constructed. It is therefore relevant to question whether a proposed design of a future calorimeter is optimal for the application of AI/ML techniques and,...
We present a smart pixel prototype readout integrated circuit (ROIC), designed in a 28 nm CMOS bulk process, featuring in-pixel implementation of a machine learning based data filtering algorithm. This serves as a proof-of-principle for future particle tracking detectors. The ROIC integrates in-pixel signal processing with a fully connected two-layer neural network that analyzes information...
We present decision trees designs that are optimized for FPGA in high energy physics trigger systems. Designs for classification, regression, anomaly detection, which occupy O(1)% resources and execute at 10s of nanoseconds, are presented. Four papers are summarized: Hong et al., JINST 16, P08016 (2021) http://doi.org/10.1088/1748-0221/16/08/P08016; Carlson et al., JINST 17, P09039 (2022)...
Central Drift Chamber in the Belle II experiment is one of the charged tracking device for not only offline but also real-time trigger systems. In the operation so far, we observe an issue of cross-talk noise in the Front-End Electronics device, where a bunch of noise wire hits happen in nearby regions. This issue causes fake tracks in hardware trigger and also increases the processing loading...
Integration of machine learning (ML) algorithms within the front-end ASICs used for charge detection and readout in high-energy and nuclear physics experiments can alleviate data transfer bottlenecks to back-end data acquisition systems. By only transmitting higher-level signal features inferred from the front-end signals (such as amplitude, time constant, time of arrival, or even particle...
The 40MeV linear accelerator and 3$\mu$m free-electron laser (FEL) facility at UH offers a versatile platform for advanced beam physics experiments and compact radiation source development. In this talk, I will discuss opportunities for applying AI and machine learning methods to optimize key beam parameters critical for the performance of the FEL and the inverse Compton scattering (ICS)....
The axion is a compelling hypothetical particle that could account for some or all of the dark matter in our universe, while simultaneously explaining why quark interactions within the neutron do not appear to give rise to an electric dipole moment. The most sensitive axion detection technique in the 4-40 ueV mass range makes use of the axion-photon coupling and is called the axion cavity...
This report will present an idea of implementing a general form of Neural Network in a digital ASIC. As High-Level-Synthesis has been a popular approach for ML inference to FPGA, we use HDL to construct a Neural Network into a pure RTL design, where the network is parameterized as a general form. This design is expected to be utilized not only in FPGA but also as a digital ASIC. We will...
PHYS476 is an upper-division undergraduate course at the University of Hawai‘i at Mānoa designed to introduce physics majors to modern electronics and its applications in experimental science. The course integrates hands-on lab work with theoretical lectures to provide students with practical experience in digital circuit design, FPGA programming, and machine learning applications for...
