About

Alexander Veidenbaum is a professor in the Department of Computer Science at UC Irvine's Donald Bren School of Information & Computer Sciences. His research focuses on computer architecture, embedded systems, and compilers, with particular emphasis on developing new methods to build high-performance computers and to compile for them. His work investigates various aspects of computer system definition, design, and optimization, especially targeting parallel systems. Dr. Veidenbaum earned his Ph.D. from the University of Illinois at Urbana-Champaign in 1985.

Research topics

• Computer Science
• Artificial Intelligence
• Medicine
• Internal medicine
• Pathology
• Engineering
• Machine Learning
• Programming language
• Radiology
• Communication
• World Wide Web
• Human–computer interaction
• Multimedia
• Intensive care medicine
• Systems engineering
• Psychology

Selected publications

• Grammar Pruning: Enabling Low-Latency Zero-Shot Task-Oriented Language Models for Edge AI

  2025-01-01

  articleOpen accessSenior author

  Edge deployment of task-oriented semantic parsers demands high accuracy under tight latency and memory budgets.We present Grammar Pruning, a lightweight zero-shot framework that begins with a user-defined schema of API calls and couples a rule-based entity extractor with an iterative grammar-constrained decoder: extracted items dynamically prune the context-free grammar, limiting generation to only those intents, slots, and values that remain plausible at each step.This aggressive searchspace reduction both reduces hallucinations and slashes decoding time.On the adapted FoodOrdering, APIMIXSNIPS, and APIMIXATIS benchmarks, Grammar Pruning with small language models achieves an average execution accuracy of over 90%-rivaling State-of-the-Art, cloud-based solutions-while sustaining at least 2x lower end-to-end latency than existing methods.By requiring nothing beyond the domain's full API schema values yet delivering precise, real-time natural-language understanding, Grammar Pruning positions itself as a practical building block for future edge-AI applications that cannot rely on large models or cloud offloading.

  PublisherOA PDFDOI

• A Multiple Compiler Framework for Improved Performance

  Lecture notes in computer science · 2025-10-31

  book-chapterSenior author
  PublisherDOI

• Using Hyperdimensional Computing to Extract Features for the Detection of Type 2 Diabetes

  2023-05-01 · 6 citations

  articleSenior author

  Diabetes impacts around 8% of the world’s population, with Type 2 diabetes comprising up to 90% of cases. This chronic disease is characterized by a metabolic resistance to insulin which results in a high blood sugar level and increased potential for serious health complications. Preventative medicine and the detection of genetic predisposition play a key part in successful treatment. Although several factors have been identified as possible indicators of underlying diabetes, they are not the same in every patient. There have been different approaches to producing predictive models that could help identify risk of onset diabetes. Models built using Machine Learning algorithms have showed promise in the past in detecting relevant features in sample datasets with data from patients at risk of developing diabetes. However, overall performance has not been consistent across datasets. In this paper we describe a feature extraction approach using Hyperdimensional Computing as a tool for improving already existing classification models. We tested our approach using two public datasets and compare across several state of the art models. Our approach improves poor performing models while fine tuning models with a high classification accuracy.

  PublisherDOI

• Enhancing the Privacy of Machine Learning via faster arithmetic over Torus FHE

  2023-07-01

  articleSenior author

  The increased popularity of Machine Learning as a Service (MLaaS) makes the privacy of user data and network weights a critical concern. Using Torus FHE (TFHE) [1] offers a solution for privacy-preserving computation in a cloud environment by allowing computation directly over encrypted data. However, software TFHE implementations of cyphertext-cyphertext multiplication needed when both input data and weights are encrypted are either lacking or are too slow. This paper proposes a new way to improve the performance of such multiplication by applying carry save addition. Its theoretical speedup is proportional to the bit width of the plaintext integer operands. This also speeds up multi-operand summation. A speedup of 15x is obtained for 16-bit multiplication on a 64-core processor, when compared to previous results. Multiplication also becomes more than twice as fast on a GPU if our approach is utilized. This leads to much faster dot product and convolution computations, which combine multiplications and a multi-operand sum. A 45x speedup is achieved for a 16-bit, 32element dot product and $\mathrm{a}\sim 30\mathrm{x}$ speedup for a convolution with a 32x32 filter size.

  PublisherDOI

• A Heterogeneous Solution to the All-pairs Shortest Path Problem using FPGAs

  2022 23rd International Symposium on Quality Electronic Design (ISQED) · 2022-04-06 · 2 citations

  article

  Heterogeneous systems present exciting new opportunities for graph and Machine Learning applications. This paper presents a novel approach for the All-pairs Shortest Path (APSP) computation using a heterogeneous CPU-FPGA Accelerator sys-tem. It is based on a recursive variant of Kleene’s APSP algorithm. Carefully re-engineering the algorithm to exploit parallelism in both the Floyd-Warshall algorithm and the general Kleene algorithm to perform Floyd-Warshall and Matrix-Multiply on the FPGA while the CPU efficiently balances the communication and computation between the kernels, improves state-of-the-art performance on FPGAs for APSP, while achieving near-GPU levels of performance, with less power and hardware resources, and out-performs the CPU-only solution by over 137x for a 8192x8192 problem size. When adjusted for power draw differences in process nodes, it also surpasses the GPU implementation in terms of performance per Watt by over 13%.

  PublisherDOI

• Class-Modeling of Septic Shock With Hyperdimensional Computing

  medRxiv · 2021-05-25

  preprintOpen accessSenior author

  Abstract Sepsis arises when a patient’s immune system has an extreme reaction to an infection. This is followed by septic shock if damage to organ tissue is so extensive that it causes a total systemic failure. Early detection of septic shock among septic patients could save critical time for preparation and prevention treatment. Due to the high variance in symptoms and patient state before shock, it is challenging to create a protocol that would be effective across patients. However, since septic shock is an acute change in patient state, modeling patient stability could be more effective in detecting a condition that departs from it. In this paper we present a one-class classification approach to septic shock using hyperdimensional computing. We built various models that consider different contexts and can be adapted according to a target priority. Among septic patients, the models can detect septic shock accurately with 90% sensitivity and overall accuracy of 60% of the cases up to three hours before the onset of septic shock, with the ability to adjust predictions according to incoming data. Additionally, the models can be easily adapted to prioritize sensitivity (increase true positives) or specificity (decrease false positives).

  PublisherOA PDFDOI

• Detecting COVID-19 Related Pneumonia on CT Scans using Hyperdimensional Computing

  medRxiv · 2021-05-25 · 2 citations

  preprintOpen accessSenior author

  Abstract Pneumonia is a common complication associated with COVID-19 infections. Unlike common versions of pneumonia spread quickly through large lung regions, COVID-19 related pneumonia starts in small localized pockets before spreading over the course of several days. This makes the infection more resilient and with a high probability of developing acute respiratory distress syndrome. Because of the peculiar spread pattern, the use of pulmonary computerized tomography (CT) scans was key in identifying COVID-19 infections. Identifying uncommon pulmonary diseases could be a strong line of defense in early detection of new respiratory infection-causing viruses. In this paper we describe a classification algorithm based on hyperdimensional computing for the detection of COVID-19 pneumonia in CT scans. We test our algorithm using three different datasets. The highest reported accuracy is 95.2% with an F1 score of 0.90, and all three models had a precision of 1 (0 false positives).

  PublisherOA PDFDOI

• Class-Modeling of Septic Shock With Hyperdimensional Computing

  2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) · 2021 · 6 citations

  Senior authorCorresponding
  • Computer Science
  • Machine Learning
  • Medicine

  Sepsis arises when a patient's immune system has an extreme reaction to an infection. This is followed by septic shock if damage to organ tissue is so extensive that it causes a total systemic failure. Early detection of septic shock among septic patients could save critical time for preparation and prevention treatment. Due to the high variance in symptoms and patient state before shock, it is challenging to create a protocol that would be effective across patients. However, since septic shock is an acute change in patient state, modeling patient stability could be more effective in detecting a condition that departs from it. In this paper we present a one-class classification approach to septic shock using hyperdimensional computing. We built various models that consider different contexts and can be adapted according to a target priority. Among septic patients, the models can detect septic shock accurately with 90% sensitivity and overall accuracy of 60% of the cases up to three hours before the onset of septic shock, with the ability to adjust predictions according to incoming data. Additionally, the models can be easily adapted to prioritize sensitivity (increase true positives) or specificity (decrease false positives).

  PublisherDOI

• EdgeAvatar: An Edge Computing System for Building Virtual Beings

  Electronics · 2021 · 8 citations

  Senior authorCorresponding
  • Computer Science
  • Artificial Intelligence
  • Computer Science

  Dialogue systems, also known as conversational agents, are computing systems that use algorithms for speech and language processing to engage in conversation with humans or other conversation-capable systems. A chatbot is a conversational agent that has, as its primary goal, to maximize the length of the conversation without any specific targeted task. When a chatbot is embellished with an artistic approach that is meant to evoke an emotional response, then it is called a virtual being. On the other hand, conversational agents that interact with the physical world require the use of specialized hardware to sense and process captured information. In this article we describe EdgeAvatar, a system based on Edge Computing principles for the creation of virtual beings. The objective of the EdgeAvatar system is to provide a streamlined and modular framework for virtual being applications that are to be deployed in public settings. We also present two implementations that use EdgeAvatar and are inspired by historical figures to interact with visitors of the Venice Biennale 2019. EdgeAvatar can adapt to fit different approaches for AI powered conversations.

  PublisherOA PDFDOI

• Detecting COVID-19 Related Pneumonia On CT Scans Using Hyperdimensional Computing

  2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) · 2021 · 14 citations

  Senior authorCorresponding
  • Computer Science
  • Artificial Intelligence
  • Medicine

  Pneumonia is a common complication associated with COVID-19 infections. Unlike common versions of pneumonia that spread quickly through large lung regions, COVID-19 related pneumonia starts in small localized pockets before spreading over the course of several days. This makes the infection more resilient and with a high probability of developing acute respiratory distress syndrome. Because of the peculiar spread pattern, the use of pulmonary computerized tomography (CT) scans was key in identifying COVID-19 infections. Identifying uncommon pulmonary diseases could be a strong line of defense in early detection of new respiratory infection-causing viruses. In this paper we describe a classification algorithm based on hyperdimensional computing for the detection of COVID-19 pneumonia in CT scans. We test our algorithm using three different datasets. The highest reported accuracy is 95.2% with an F1 score of 0.90, and all three models had a precision of 1 (0 false positives).

  PublisherDOI

Recent grants

• XPS: FULL: FP: Collaborative Research: Advancing autovectorization

  NSF · $338k · 2015–2020

• A Framework for Speeding Up Mobile Code Execution in Embedded Systems Using Superoperators and Annotations

  NSF · $299k · 2003–2008

Frequent coauthors

• Alexandru Nicolau

  58 shared

• Arun Kejariwal

  21 shared

• Rosario Cammarota

  Intel (United States)

  13 shared

• Neftali Watkinson

  University of California, Riverside

  13 shared

• Constantine D. Polychronopoulos

  Verizon (United States)

  10 shared

• Utpal Banerjee

  9 shared

• Xinmin Tian

  9 shared

• Elana D. Granston

  University of Illinois Urbana-Champaign

  8 shared