25–28 Sept 2023
Imperial College London
Europe/London timezone

Contribution List

82 out of 82 displayed
Export to PDF
  1. 25/09/2023, 08:30
  2. Alex Tapper (Imperial College London), Sioni Paris Summers (CERN)
    25/09/2023, 09:30
  3. Thea Aarrestad (ETH Zurich (CH))
    25/09/2023, 09:45
    Invited Talks
  4. Steve Aplin (EuXFEL)
    25/09/2023, 11:00
    Invited Talks
  5. Maria Brbic
    25/09/2023, 11:45
    Invited Talks

    Biomedical data poses multiple hard challenges that break conventional machine learning assumptions. In this talk, I will highlight the need to transcend our prevalent machine learning paradigm and methods to enable them to become the driving force of new scientific discoveries. I will present machine learning methods that have the ability to bridge heterogeneity of individual biological...

    Go to contribution page
  6. Prof. Audrey Corbeil Therrien (Université de Sherbrooke)
    25/09/2023, 13:30
    Contributed Talks
    Standard Talk

    As detector technologies improve, the increase in resolution, number of channels and overall size create immense bandwidth challenges for the data acquisition system, long data center compute times and growing data storage costs. Much of the raw data does not contain useful information and can be significantly reduced with veto and compression systems as well as online analysis.

    We design...

    Go to contribution page
  7. Farouk Mokhtar (Univ. of California San Diego (US))
    25/09/2023, 13:45
    Contributed Talks
    Standard Talk

    Particle flow reconstruction is crucial to analyses performed at general-purpose detectors, such as ATLAS and CMS. Recent developments have shown that a machine-learned particle-flow reconstruction using graph neural networks offer a prospect for computationally efficient event reconstruction [1-2]. Focusing on scalability of machine-learning based models for full event reconstruction, we...

    Go to contribution page
  8. Santosh Parajuli (Univ. Illinois at Urbana Champaign (US))
    25/09/2023, 14:00
    Contributed Talks
    Standard Talk

    The High-Luminosity LHC (HL-LHC) will provide an order of magnitude increase in integrated luminosity and enhance the discovery reach for new phenomena. The increased pile-up foreseen during the HL-LHC necessitates major upgrades to the ATLAS detector and trigger. The Phase-II trigger will consist of two levels, a hardware-based Level-0 trigger and an Event Filter (EF) with tracking...

    Go to contribution page
  9. Rachel Kovach-Fuentes (University of Chicago)
    25/09/2023, 14:15
    Contributed Talks
    Standard Talk

    The combinatorics of track seeding has long been a computational bottleneck for triggering and offline computing in High Energy Physics (HEP), and remain so for the HL-LHC. Next-generation pixel sensors will be sufficiently fine-grained to the point of being able to determine angular information of the charged particle passing through. This detector technology immediately improves the...

    Go to contribution page
  10. William Patrick Mccormack (Massachusetts Inst. of Technology (US))
    25/09/2023, 14:30
    Contributed Talks
    Standard Talk

    Computing demands for large scientific experiments, such as the CMS experiment at CERN, will increase dramatically in the next decades. To complement the future performance increases of software running on CPUs, explorations of coprocessor usage in data processing hold great potential and interest. We explore the novel approach of Services for Optimized Network Inference on Coprocessors...

    Go to contribution page
  11. Jeffrey Krupa (Massachusetts Institute of Technology)
    25/09/2023, 14:45
    Contributed Talks
    Standard Talk

    Due to the stochastic nature of hadronic interactions, particle showers from hadrons can vary greatly in their size and shape. Recovering all energy deposits from a hadronic shower within a calorimeter into a single cluster can be challenging and requires an algorithm that accommodates the large variation present in such showers. In this study, we demonstrate the potential of a deep learning...

    Go to contribution page
  12. Anne-Sophie Berthold (Technische Universitaet Dresden (DE))
    25/09/2023, 15:30
    Contributed Talks
    Standard Talk

    In 2026 the Phase-II Upgrade will enhance the LHC to become the High Luminosity LHC. Its luminosity will be up to 7 times of the nominal LHC luminosity. This leads to an increase in interesting events which might open the door to detect new physics. However, it also leads to a major increase in proton-proton collisions with mostly low energetic hadronic particles, called pile-up. Up to 200...

    Go to contribution page
  13. Thomas Owen James (CERN)
    25/09/2023, 15:45
    Contributed Talks
    Standard Talk

    A novel data collection system, known as Level-1 (L1) Scouting, is being introduced as part of the L1 trigger of the CMS experiment at the CERN LHC. The L1 trigger of CMS, implemented in FPGA-based hardware, selects events at 100 kHz for full read-out, within a short 3 microsecond latency window. The L1 Scouting system collects and stores the reconstructed particle primitives and intermediate...

    Go to contribution page
  14. Andrew George Oliver
    25/09/2023, 16:00
    Contributed Talks
    Standard Talk

    Decision Forests are fast and effective machine learning models for making real time predictions. In the context of the hardware triggers of the experiments at the Large Hadron Collider, DF inference is deployed on FPGA processors with sub-microsecond latency requirements. The FPGAs may be executing many algorithms, and many DFs, motivating resource-constrained inference. Using a jet tagging...

    Go to contribution page
  15. Tae Min Hong (University of Pittsburgh (US))
    25/09/2023, 16:15
    Contributed Talks
    Standard Talk

    We introduce the fwXmachina framework for evaluating boosted decision trees on FPGA for implementation in real-time systems. The software and electrical engineering designs are introduced, with both physics and firmware performance detailed. The test bench setup is described. We present an example problem in which fwXmachina may be used to improve the identification of vector boson fusion...

    Go to contribution page
  16. Chang Sun (ETH Zurich (CH))
    25/09/2023, 16:30
    Contributed Talks
    Standard Talk

    We present the preparation, deployment, and testing of an autoencoder trained for unbiased detection of new physics signatures in the CMS experiment Global Trigger test crate FPGAs during LHC Run 3. The Global Trigger makes the final decision whether to readout or discard the data from each LHC collision, which occur at a rate of 40 MHz, within a 50 ns latency. The Neural Network makes a...

    Go to contribution page
  17. Stephen Roche (Saint Louis University)
    25/09/2023, 17:00
    Contributed Talks
    Lightning Talk

    We describe an application of the deep decision trees, described in fwXmachina part 1 and 2 at this conference, in fwXmachina for anomaly detection in FPGA for implementation in real-time systems. A novel method to train the decision-tree-based autoencoder is presented. We give an example in which fwXmachina may be used to detect a variety of different BSM models via anomaly detection at the...

    Go to contribution page
  18. Graziella Russo (Sapienza Universita e INFN, Roma I (IT))
    25/09/2023, 17:05
    Contributed Talks
    Lightning Talk

    In the next years the ATLAS experiment will undertake major upgrades to cope with the expected increase of luminosity provided by the Phase II of the LHC accelerator. In particular, in the barrel of the muon spectrometer a new triplet of RPC detector will be added and the trigger logic will be performed on FPGAs. We have implemented a new CNN architecture that is able to identify the muon...

    Go to contribution page
  19. Shruti R Kulkarni (Oak Ridge National Laboratory)
    25/09/2023, 17:10
    Contributed Talks
    Lightning Talk

    This work describes the investigation of neuromorphic computing--based spiking neural network (SNN) models used to filter data from sensor electronics in the CMS experiments experiments conducted at the High Luminosity Large Hadron Collider (HL-LHC). We present our approach for developing a compact neuromorphic model that filters out the sensor data based on the particle's transverse momentum...

    Go to contribution page
  20. Micol Rigatti (Fermi National Accelerator Lab. (US))
    25/09/2023, 17:15
    Contributed Talks
    Lightning Talk

    The processing of large volumes of high precision data generated by sophisticated detectors in high-rate collisions poses a significant challenge for major high-energy nuclear and particle experiments. To address this challenge and revolutionize real-time data processing pipelines, modern deep neural network techniques and AI-centric hardware innovations are being developed.
    The sPHENYX...

    Go to contribution page
  21. Christopher Edward Brown (Imperial College (GB))
    25/09/2023, 17:20
    Contributed Talks
    Lightning Talk

    The Large Hadron Collider will be upgraded to the High Luminosity LHC, delivering many more simultaneous proton-proton collisions, extending the sensitivity to rare processes. The CMS detector will be upgraded with new, highly granular, detectors in order to maintain performance in the busy environment with many overlapping collisions (pileup). For the first time, tracks from charged particles...

    Go to contribution page
  22. Duc Minh Hoang (MIT)
    25/09/2023, 17:25
    Contributed Talks
    Lightning Talk

    The future LHC High-Luminosity upgrade amplifies the proton collision rate by a factor of about 5-7, posing challenges for physics object reconstruction and identification including tau and b-jet tagging. Detecting both the taus and bottom quarks at the CMS Level-1 (L1) trigger enhances many important physics analyses in the experiment. The challenge of the L1 trigger system requires...

    Go to contribution page
  23. Pratik Jawahar (University of Manchester (UK - ATLAS))
    25/09/2023, 17:30
    Contributed Talks
    Lightning Talk

    Data storage is a major limitation at the Large Hadron Collider and is currently addressed by discarding a large fraction of data. We present an autoencoder based lossy compression algorithm as a first step towards a solution to mitigate this problem, potentially enabling storage of more events. We deploy an autoencoder model, on Field Programmable Gate Array (FPGA) firmware using the hls4ml...

    Go to contribution page
  24. Claire Savard (University of Colorado Boulder (US))
    25/09/2023, 17:35
    Contributed Talks
    Lightning Talk

    With machine learning gaining more and more popularity as a physics analysis tool, physics computing centers, such as the Fermilab LHC Physics Center (LPC), are seeing huge increases in their resources being used for such algorithms. These facilities, however, are not generally set up efficiently for machine learning inference as they rely on slower CPU evaluation, which has a noticeable...

    Go to contribution page
  25. Denis-Patrick Odagiu (ETH Zurich (CH))
    25/09/2023, 17:40
    Contributed Talks
    Lightning Talk

    The upcoming high-luminosity upgrade of the LHC will lead to a factor of five increase in instantaneous luminosity during proton-proton collisions. Consequently, the experiments situated around the collider ring, such as the CMS experiment, will record approximately ten times more data. Furthermore, the luminosity increase will result in significantly higher data complexity, thus making more...

    Go to contribution page
  26. Mr Ryan Liu (University of California, Berkeley)
    25/09/2023, 17:45
    Contributed Talks
    Lightning Talk

    The challenging environment of real-time systems at the Large Hadron Collider (LHC) strictly limits the computational complexity of algorithms that can be deployed. For deep learning models, this implies only smaller models that have lower capacity and weaker inductive bias are feasible. To address this issue, we utilize knowledge distillation to leverage both the performance of large models...

    Go to contribution page
  27. Stefano Franchellucci (Universite de Geneve (CH))
    25/09/2023, 17:50
    Contributed Talks
    Lightning Talk

    The exceptional challenges in data acquisition faced by experiments at the LHC demand extremely robust trigger systems. The ATLAS trigger, after a fast hardware data processing step, uses software-based selections referred to as the High-Level-Trigger (HLT). Jets originating from b-quarks (b-jets) are produced in many interesting fundamental interactions, making them a key signature in a broad...

    Go to contribution page
  28. David Reikher (Tel Aviv University (IL))
    25/09/2023, 17:55
    Contributed Talks
    Lightning Talk

    BDTs are simple yet powerful ML algorithms with performance often at par with cutting-edge NN-based models. The structure of BDTs allows for a highly parallelized, low-latency implementation in FPGAs. I will describe the development and implementation of a BDT-based algorithm for tau lepton identification in the ATLAS Level-1 trigger system as part of the phase-I upgrade, designed to be...

    Go to contribution page
  29. Maciej Mikolaj Glowacki (University of Bristol (GB))
    25/09/2023, 18:00
    Contributed Talks
    Lightning Talk

    The High Luminosity upgrade to the LHC will deliver unprecedented luminosity to the experiments, culminating in up to 200 overlapping proton-proton collisions. In order to cope with this challenge several elements of the CMS detector are being completely redesigned and rebuilt. The Level-1 Trigger is one such element; it will have a 12.5 microsecond window in which to process protons colliding...

    Go to contribution page
  30. Jovan Mitrevski (Fermi National Accelerator Lab. (US))
    25/09/2023, 18:05
    Contributed Talks
    Lightning Talk

    Extracting low-energy signals from LArTPC detectors is useful, for example, for detecting supernova events or calibrating the energy scale with argon-39. However, it is difficult to efficiently extract the signals because of noise. We propose using a 1DCNN to select wire traces that have a signal. This efficiently suppresses the background while still being efficient for the signal. This is...

    Go to contribution page
  31. Jan-Frederik Schulte (Purdue University (US))
    25/09/2023, 18:10
    Contributed Talks
    Lightning Talk

    Graph structures are a natural representation of data in many fields of research, including particle and nuclear physics experiments, and graph neural networks (GNNs) are a popular approach to extract information from that. Simultaneously, there is often a need for very low-latency evaluation of GNNs on FPGAs. The HLS4ML framework for translating machine learning models from industry-standard...

    Go to contribution page
  32. Luke McDermott (UC San Diego & Modern Intelligence)
    25/09/2023, 18:15
    Contributed Talks
    Lightning Talk

    Within the framework of the L1 trigger's data filtering mechanism, ultra-fast autoencoders are instrumental in capturing new physics anomalies. Given the immense influx of data at the LHC, these networks must operate in real-time, making rapid decisions to sift through vast volumes of data. Meeting this demand for speed without sacrificing accuracy becomes essential, especially when...

    Go to contribution page
  33. Sitian Qian (Peking University (CN))
    25/09/2023, 18:20
    Contributed Talks
    Lightning Talk

    Recent years have witnessed the enormous success of the transformer models in various research fields including Natural Language Processing, Computational Vision as well as natural science territory. In the HEP community, models with transformer backbones have shown their power in jet tagging tasks. However, despite the impressive performance, transformer-based models are often large and...

    Go to contribution page
  34. Karin Rathsman (European Spallation Source)
    26/09/2023, 09:00
    Invited Talks
    Standard Talk

    The European Spallation Source (ESS) is multi-disciplinary research facility based on neutron scattering under construction in Lund. The facility includes a superconducting linear proton accelerator, a rotating tungsten target wheel where neutrons are spalled off by the high energy protons and a suit of instruments for neutron scattering experiments.

    ESS is a user facility designed and...

    Go to contribution page
  35. Matt Streeter
    26/09/2023, 09:45
    Invited Talks
  36. Jonathan Citrin
    26/09/2023, 11:00
    Invited Talks

    Magnetic confinement fusion research is at a threshold where the next generation of experiments are designed to deliver burning fusion plasmas with net energy gain for the first time. ML holds great promise in reducing the costs and risks of fusion reactor development, by enabling efficient workflows for scenario optimization, reactor design, and controller design. This talk reviews various...

    Go to contribution page
  37. Ingo Waldmann (UCL), Kai Hou Yip
    26/09/2023, 11:45
    Invited Talks

    The exploration of extrasolar planets, which are planets orbiting stars other than our own, holds great potential for unravelling long-standing mysteries surrounding planet formation, habitability, and the emergence of life in our galaxy. By studying the atmospheres of these exoplanets, we gain valuable insights into their climates, chemical compositions, formation processes, and past...

    Go to contribution page
  38. Sabin Anton (Imperial College London, Department of Aeronautics, Postgraduate Student)
    26/09/2023, 13:30
    Contributed Talks
    Standard Talk

    The field of Astrodynamics faces a significant challenge due to the increasing number of space objects orbiting Earth, especially from recent satellite constellation deployments. This surge underscores the need for quicker and more efficient algorithms for orbit propagation and determination to mitigate collision risks in both Earth-bound and interplanetary missions on large scales. Often,...

    Go to contribution page
  39. Keneth Stiven Garcia Cifuentes (Universidad Nacional Autónoma de México)
    26/09/2023, 13:45
    Contributed Talks
    Standard Talk

    Gamma-ray bursts (GRBs) have traditionally been categorized based on their durations. However, the emergence of extended emission (EE) GRBs, characterized by durations higher than two seconds and properties similar to short GRBs, challenges conventional classification methods. In this talk, we delve into GRB classification, focusing on a machine-learning technique (t-distributed stochastic...

    Go to contribution page
  40. Katya Govorkova (Massachusetts Inst. of Technology (US))
    26/09/2023, 14:00
    Contributed Talks
    Standard Talk

    Deep Learning assisted Anomaly detection is quickly becoming a powerful tool allowing for the rapid identification of new phenomena.
    We present a method of anomaly detection techniques based on deep recurrent autoencoders to the problem of detecting gravitational wave signals in laser interferometers. This class of algorithm is trained via a semi-supervised strategy, i.e. with a weak...

    Go to contribution page
  41. Eric Anton Moreno (Massachusetts Institute of Technology (US))
    26/09/2023, 14:15
    Contributed Talks
    Standard Talk

    Deep Learning (DL) applications for gravitational-wave (GW) physics are becoming increasingly common without the infrastructure to be validated at-scale or deployed in real-time. With ever more sensitive GW observing runs beginning in 2023, the tradeoff between speed and data robustness must be bridged in order to create experimental pipelines which take shorter to iterate upon and which...

    Go to contribution page
  42. Maira Khan
    26/09/2023, 14:30
    Contributed Talks
    Standard Talk

    The Deep Underground Neutrino Experiment (DUNE) presents promising approaches to better identify and understand supernova (SN) events. Using simulated Liquid Argon Time Projection Chamber (LarTPC) data, we develop an end to end edge-AI pipeline that has the potential to significantly reduce SN pointing time. Using a sequence of machine learning algorithms, we are able to reject radiological...

    Go to contribution page
  43. Jovan Mitrevski (Fermi National Accelerator Lab. (US))
    26/09/2023, 14:45
    Contributed Talks
    Standard Talk

    In the Fermilab accelerator complex, the Main Injector (MI) and the Recycler Ring (RR) share a tunnel. The initial design was made for the needs of the Tevatron, where the RR stored fairly low intensities of anti-protons. Currently, however, both the MI and RR often have high intensity beams at the same time. Beam loss monitors (BLMs) are placed at different points in the tunnel to detect...

    Go to contribution page
  44. Maira Khan
    26/09/2023, 15:00
    Contributed Talks
    Standard Talk

    Superconducting (SC) magnets deployed at any accelerator complex must reach exceptionally high currents to accurately control particle trajectories. During operation, superconducting magnets occasionally experience a spontaneous transition from the superconducting to the normal state while operating at several kiloamps (quenching). Quenches may significantly damage the magnet, preventing SC...

    Go to contribution page
  45. Ryan Forelli (Lehigh University)
    26/09/2023, 15:15
    Contributed Talks
    Standard Talk

    The Tokamak magnetic confinement fusion device is one leading concept design for future fusion reactors which require extremely careful control of plasma parameters and magnetic fields to prevent fatal instabilities. Magneto-hydrodynamic (MHD) instabilities occur when plasma confinement becomes unstable as a result of distorted non-axisymmetric magnetic field lines. These ``mode''...

    Go to contribution page
  46. Ronan Docherty (Imperial College London)
    26/09/2023, 16:00
    Contributed Talks
    Standard Talk

    Segmentation is the assigning of a semantic class to every pixel in an image, and is a prerequisite for downstream analysis like phase quantifcation, morphological characterization etc. The wide range of length scales, imaging techniques and materials studied in materials science means any segmentation algorithm must generalise to unseen data and support abstract, user-defined semantic...

    Go to contribution page
  47. Veronica Obute (Drexel)
    26/09/2023, 16:15
    Contributed Talks
    Standard Talk

    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
  48. Prof. Joshua Agar (Drexel)
    26/09/2023, 16:30
    Contributed Talks
    Standard Talk

    Materials have marked human evolution throughout history. The next technological advancement will inevitably be based on a groundbreaking material. Future discovery and application of materials in technology necessitates precise methods capable of creating long-range, non-equilibrium structures with atomic accuracy. To achieve this, we need enhanced analysis tools and swift automated...

    Go to contribution page
  49. Dr Fangxin Fang (Imperial College London)
    26/09/2023, 16:45
    Contributed Talks
    Standard Talk

    Accurate and reliable long-term operational forecasting is of paramount importance in numerous domains, including weather prediction, environmental monitoring, early warning of hazards, and decision-making processes. Spatiotemporal forecasting involves generating temporal forecasts for system state variables across spatial regions. Data-driven methods such as Convolutional Long Short-Term...

    Go to contribution page
  50. Miguel Xochicale (University College London)
    26/09/2023, 17:00
    Contributed Talks
    Standard Talk

    Surgical data technologies have not only been successfully integrated inputs from various data sources (e.g., medical devices, trackers, robots and cameras) but have also applied a range of machine learning and deep learning methods (e.g., classification, segmentation or synthesis) to data-driven interventional healthcare. However, the diversity of data, acquisitions and pre-processing...

    Go to contribution page
  51. Matthew Foulkes (Imperial College London)
    26/09/2023, 17:15
    Contributed Talks
    Standard Talk

    The use of neural networks for approximating fermionic wave functions has become popular over the past few years as their ability to provide impressively accurate descriptions of molecules, nuclei, and solids has become clear.

    Most electronic structure methods rely on uncontrolled approximations, such as the choice of exchange-correlation functional in density functional theory or the form...

    Go to contribution page
  52. Prof. Guosheng Yin (Department of Mathematics Imperial College London), Guosheng Yin (Department of Mathematics Imperial College London)
    26/09/2023, 17:30
    Contributed Talks
    Lightning Talk

    High-dimensionality is known to be the bottleneck for both nonparametric regression and Delaunay triangulation. To efficiently exploit the geometric information for nonparametric regression without conducting the Delaunay triangulation for the entire feature space, we develop the crystallization search for the neighbour Delaunay simplices of the target point similar to crystal growth. We...

    Go to contribution page
  53. Zehui Li
    26/09/2023, 17:35
    Contributed Talks
    Lightning Talk

    Given the increasing volume and quality of genomics data, extracting new insights requires efficient and interpretable machine-learning models. This work presents Genomic Interpreter: a novel architecture for genomic assay prediction. This model out-performs the state-of-the-art models for genomic assay prediction tasks. Our model can identify hierarchical dependencies in genomic sites. This...

    Go to contribution page
  54. Lupe Fiasco
    26/09/2023, 19:00

    Wasalu Jaco, professionally known as Lupe Fiasco, is a Chicago-born, Grammy Award-winning American rapper, record producer, entrepreneur, and community advocate. He is a luminary in the world of hip-hop, renowned for his thought-provoking lyrics, innovative storytelling, and unwavering commitment to social and political activism.

    Rising to fame in 2006, following the success of his debut...

    Go to contribution page
  55. Yaman Umuroglu
    27/09/2023, 09:00
    Invited Talks

    Beyond the well-known highlights in computer vision and natural language, AI is steadily expanding into new application domains. This Pervasive AI trend requires supporting diverse and fast-moving application requirements, ranging from specialized I/O to fault tolerance and limited resources, all the while retaining high performance and low latency. Adaptive compute architectures such as AMD...

    Go to contribution page
  56. Noa Zilberman
    27/09/2023, 09:45
    Invited Talks

    How fast should your machine learning be? ideally, as fast as you can stream data to it.
    In this presentation I will discuss the role of computing infrastructure in machine learning, and argue that to face the growing volume of data and support latency constraints, the best place for inference is within the network. I will introduce in-network machine learning, the offloading of machine...

    Go to contribution page
  57. Tobias Becker (Maxeler Technologies)
    27/09/2023, 11:00
    Invited Talks

    Large Language Models (LLMs) will completely transform the way we interact with computers, but in order to be successful they need to be fast and highly responsive. This represents a significant challenge due to the extremely high computational requirements of running LLMs. In this talk, we look at the technology behind LLMs, its challenges, and why Groq's AI accelerator chip holds a...

    Go to contribution page
  58. Chen Qin
    27/09/2023, 11:45
    Invited Talks

    Deep learning has shown great potential in improving and accelerating the entire medical imaging workflow, from image acquisition to interpretation. This talk will focus on the recent advances of deep learning in medical imaging, from the reconstruction of accelerated signals to automatic quantification of clinically useful information. The talk will describe how model-based deep learning can...

    Go to contribution page
  59. Benjamin Ramhorst (Imperial College London)
    27/09/2023, 13:30
    Contributed Talks
    Standard Talk

    Neural networks achieve state-of-the art performance in image classification, medical analysis, particle physics and many more application areas. With the ever-increasing need for faster computation and lower power consumption, driven by real-time systems and Internet-of-Things (IoT), field-programmable gate arrays (FPGAs) have emerged as suitable accelerators for deep learning applications....

    Go to contribution page
  60. Cheng ZHANG (Imperial College London), Mr Jianyi Cheng (University of Cambridge)
    27/09/2023, 13:45
    Contributed Talks
    Standard Talk

    Today’s deep learning models consume considerable computation and memory resources, leading to significant energy consumption. To address the computation and memory challenges, quantization is often used for storing and computing data as few as possible. However, exploiting efficient quantization for computing a given ML model is challenging, because it affects both the computation accuracy...

    Go to contribution page
  61. Chang Sun (ETH Zurich (CH))
    27/09/2023, 14:00
    Contributed Talks
    Standard Talk

    For many deep learning applications, model size and inference speed at deployment time become a major challenge. To tackle these issues, a promising strategy is quantization.
    A straightforward uniform quantization to very low precision often results in considerable accuracy loss. A solution to this predicament is the usage of mixed-precision quantization, founded on the idea that certain...

    Go to contribution page
  62. Dr Menouar Azib (Akkodis)
    27/09/2023, 14:15
    Contributed Talks
    Standard Talk

    Event detection in time series data plays a crucial role in various domains, including finance, healthcare, environmental monitoring, cybersecurity, and science. Accurately identifying and understanding events in time series data is vital for making informed decisions, detecting anomalies, and predicting future trends. Extensive research has explored diverse methods for event detection in time...

    Go to contribution page
  63. Olivia Weng
    27/09/2023, 14:30
    Contributed Talks
    Standard Talk

    Scientific experiments rely on machine learning at the edge to process extreme volumes of real-time streaming data. Extreme edge computation often requires robustness to faults, e.g., to function correctly in high radiation environments or to reduce the effects of transient errors. As such, the computation must be designed with fault tolerance as a primary objective. FKeras is a tool that...

    Go to contribution page
  64. Mr Rizwan Tariq Syed (IHP - Leibniz-Institut für innovative Mikroelektronik), Dr Marko Andjelkovic (IHP - Leibniz-Institut für innovative Mikroelektronik), Dr Markus Ulbricht (IHP - Leibniz-Institut für innovative Mikroelektronik), Prof. Milos Krstic (IHP - Leibniz-Institut für innovative Mikroelektronik)
    27/09/2023, 14:45
    Contributed Talks
    Standard Talk

    There has been a growing trend of Multi-Modal AI models capable of gathering data from multiple sensor modalities (cameras, lidars, radars, etc.) and processing it to give more comprehensive output and predictions. Neural Network models, such as Transformers, Convolutional neural networks (CNNs), etc., exhibit the property to process data from multiple modalities and have enhanced various...

    Go to contribution page
  65. Marta Andronic (Imperial College London)
    27/09/2023, 15:00
    Contributed Talks
    Standard Talk

    Field-programmable gate arrays (FPGAs) are widely used to implement deep learning inference. Standard deep neural network inference involves the computation of interleaved linear maps and nonlinear activation functions. Prior work for ultra-low latency implementations has hardcoded the combination of linear maps and nonlinear activations inside FPGA lookup tables (LUTs). Our work is motivated...

    Go to contribution page
  66. Freddie Renyard (University of Bristol)
    27/09/2023, 15:15
    Contributed Talks
    Standard Talk

    Machine learning has been applied to many areas of clinical medicine, from assisting radiologists with scan interpretation to clinical early warning scoring systems. However, the possibilities of ML-assisted real time data interpretationand the hardware needed to realise it are yet to be fully explored. In this talk, possible applications of fast ML hardware to real-time medical imaging will...

    Go to contribution page
  67. Dr Tobias Becker (Maxeler Technologies)
    27/09/2023, 16:00
    Contributed Talks
    Standard Talk

    Converged compute infrastructure refers to a trend where HPC clusters are set up for both AI and traditional HPC workloads, allowing these workloads to run on the same infrastructure, potentially reducing underutilization. Here, we explore opportunities for converged compute with GroqChip, an AI accelerator optimized for running large-scale inference workloads with high throughput and...

    Go to contribution page
  68. Eric Kern (Heidelberg University), Hendrik Borras (Heidelberg University)
    27/09/2023, 16:15
    Contributed Talks
    Standard Talk

    Machine Learning has gone through major revolutionary phases over the past decade and neural networks have become state-of-the-art approaches in many applications, from computer vision to natural language processing. However, these advances come at ever-growing computational costs, in contrast, CMOS scaling is hitting fundamental limitations such as power consumption and quantum mechanical...

    Go to contribution page
  69. Javier Campos
    27/09/2023, 16:30
    Contributed Talks
    Standard Talk

    Quantum readout and control is a fundamental aspect of quantum computing that requires accurate measurement of qubit states. Errors emerge in all stages, from initialization to readout, and identifying errors in post-processing necessitates resource-intensive statistical analysis. In our work, we use a lightweight fully-connected neural network (NN) to classify states of a superconducting...

    Go to contribution page
  70. Mr Krish Agrawal (Imperial College London), Mr Zhewen Yu (Imperial College London), Mr Alexander Montgomerie-Corcoran (Imperial College London)
    27/09/2023, 16:45
    Contributed Talks
    Standard Talk

    Convolutional Neural Networks (CNNs) have been applied to a wide range of applications in high energy physics including jet tagging and calorimetry. Due to their computational intensity, a large amount of work has been done to accelerate CNNs in hardware, with FPGA devices serving as a high-performance and energy-efficient platform of choice. As opposed to a dense computation where every...

    Go to contribution page
  71. Benjamin Biggs
    27/09/2023, 17:00
    Contributed Talks
    Standard Talk

    The continued need for improvements in accuracy, throughput, and efficiency of Deep Neural Networks has resulted in a multitude of methods that make the most of custom architectures on FPGAs. These include the creation of hand-crafted networks and the use of quantization and pruning to reduce extraneous network parameters. However, with the potential of static solutions already well exploited,...

    Go to contribution page
  72. Jan Zavadil (Department of Mathematics, FNSPE, Czech Technical University in Prague.)
    27/09/2023, 17:15
    Contributed Talks
    Lightning Talk

    The contribution addresses the topic of time-series recognition, specifically comparing the conventional approach of manual feature extraction with contemporary classification methods that leverage features acquired through the training process. Employing automated feature extraction software, we attained a high-dimensional representation of a time-series, obviating the necessity of...

    Go to contribution page
  73. Dr Lukas Gonon (Imperial College London)
    27/09/2023, 17:20
    Contributed Talks
    Lightning Talk

    Universal approximation theorems are the foundations of classical neural networks,
    providing theoretical guarantees that the latter are able to approximate maps of interest.
    Recent results have shown that this can also be achieved in a quantum setting,
    whereby classical functions can be approximated by parameterised quantum circuits.
    We provide here precise error bounds for specific...

    Go to contribution page
  74. Ryan Forelli (Lehigh University)
    27/09/2023, 17:25
    Contributed Talks
    Lightning Talk

    Deep learning techniques have demonstrated remarkable performance in super resolution (SR) tasks for enhancing image resolution and granularity. These architectures extract image features with a convolutional block and add the extracted features to the upsampled input image transported through a skip connection, which is then converted from a depth to higher resolution space. However, SR can...

    Go to contribution page
  75. Philip Coleman Harris (Massachusetts Inst. of Technology (US))
    27/09/2023, 17:30
  76. Kevin Pedro (Fermi National Accelerator Lab. (US)), William Patrick Mccormack (Massachusetts Inst. of Technology (US))
    28/09/2023, 09:00

    Zoom link: https://cern.zoom.us/j/63951739685?pwd=VTdITmdvOTc3V1hyK0xPa2t6cjhUdz09

    Go to contribution page
  77. Jovan Mitrevski (Fermi National Accelerator Lab. (US)), Nhan Tran, Yaman Umuroglu
    28/09/2023, 09:00
  78. Jahanzeb Ahmad, Suleyman Demirsoy
    28/09/2023, 13:00

    This two-part tutorial presents an update on Intel HLS flow and the Intel FPGA AI Suite. In the first part, we will have a 30-minute update on how the latest oneAPI tool flow for IP authoring works. In the second part we will present Intel FPGA AI Suite and groundbreaking AI Tensor Blocks newly integrated into Intel's latest FPGA device families for deep learning inference. These...

    Go to contribution page
  79. Alexander Titterton (Graphcore)
    28/09/2023, 15:00

    More and more researchers working in fields such as drug discovery, weather forecasting, climate modelling and high-energy particle physics are looking towards AI-based approaches to enhance their applications, both in terms of accuracy and time-to-result. Furthermore, new approaches such as PINNs are revolutionising how neural networks can learn to emulate physical systems governed by...

    Go to contribution page
  80. Duc Minh Hoang (MIT)
    Contributed Talks
    Lightning Talk

    Pruning enhances neural network hardware efficiency by zeroing out weight magnitude. In order to take full advantage of pruning, efficient implementations of sparse matrix multiplication are required. The current hls4ml implementations of sparse matrix multiplication rely on either the built in high-level synthesis zero suppression operations or a coordinate list representation, which faces...

    Go to contribution page
  81. Cristopher Salvi (Imperial College London)
    Contributed Talks
    Lightning Talk

    I will consider randomly initialized controlled ResNets and show that in the infinite-width-depth limit and under appropriate rescaling of weights and biases, these architectures converge weakly to Gaussian processes indexed on path-space and with kernels realised as solutions of certain data-dependent PDEs, varying according to the choice of activation function. In the special case where the...

    Go to contribution page