Craig Michael Vineyard
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Craig Michael Vineyard has a total of 139 co-authors. Here are the top co-authors by number of shared publications:
- James Bradley Aimone
Neural Exploration and Research Laboratory, Sandia National Laboratories, Albuquerque, USA
5 shared publications - Aaron J. Hill
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
4 shared publications Albuquerque Sandia National Laboratories (Snl-Nm)
4 shared publicationsUsdoe National Nuclear Security Administration (Nnsa)
4 shared publications- Felix Wang
Sandia National Laboratories, Albuquerque, NM, USA
3 shared publications - Michael C. Krygier
Sandia National Laboratories, Albuquerque, NM, USA
3 shared publications
Latest Publications
- 25 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 73 (5) , 1888-1901
Energy-Efficient Radioisotope Identification Using Spiking Neuromorphic Systems
This work presents the development and benchmarking of energy-efficient spiking Radioisotope Identification (RIID) algorithms on neuromorphic hardware, with applications to high-performance, ultra-low-power nuclear material detection. We develop a template-based matching algorithm based on sparse coding and the Locally Competitive Algorithm (LCA) that approximates state-of-the-art RIID methods such as those found in the widely known Gamma Detector Response and Analysis Software (GADRAS). We additionally evaluate simple machine learning (ML) models for RIID which are trained through the Python RadioIsotope IDentification (PyRIID) software. These algorithms are implemented as spiking neural networks (SNNs) and deployed on neuromorphic hardware platforms, including Intel Loihi 2, SpiNNaker2, and the BrainChip Akida accelerator. To quantify performance, we evaluate these algorithms against both synthetic and real-world datasets as well as compare against traditional RIID algorithms through GADRAS. The synthetic dataset was generated through PyRIID and consists of 25 isotopes across 124 shielding configurations, and the real-world dataset consists of roughly 200 test samples spanning 7 different isotopes of interest (133Ba, 226Ra, 235U, 232Th, 238U, 239Pu, 131I). We also measure energy efficiency of these algorithms through power profiling on the neuromorphic hardware. Significantly, our neuromorphic implementations consumed less than 1 mJ per inference, representing dramatic orders of magnitude reduction in energy consumption compared to traditional ARM-based GADRAS deployments. Our results also demonstrated the robustness of our developed LCA-based approach compared to a multi-layer perceptron ML model, which excelled on synthetic data and known noise models but failed to generalize to challenging real-world data. In contrast to the GADRAS baseline performance (F1 score) of 0.623, the ML-based model only achieved 0.466, whereas the LCA-based implementation was more closely matched at 0.579. Together, these findings underscore the potential of spiking neuromorphic hardware as a transformative technology for advancing RIID implementations, offering robust, energy-efficient, and field-deployable solutions for real-world applications such as real-time nuclear material detection.
- 25 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Nuclear Science
- Vol. 73 (5) , 1888-1901
Energy-Efficient Radioisotope Identification Using Spiking Neuromorphic Systems
This work presents the development and benchmarking of energy-efficient spiking Radioisotope Identification (RIID) algorithms on neuromorphic hardware, with applications to high-performance, ultra-low-power nuclear material detection. We develop a template-based matching algorithm based on sparse coding and the Locally Competitive Algorithm (LCA) that approximates state-of-the-art RIID methods such as those found in the widely known Gamma Detector Response and Analysis Software (GADRAS). We additionally evaluate simple machine learning (ML) models for RIID which are trained through the Python RadioIsotope IDentification (PyRIID) software. These algorithms are implemented as spiking neural networks (SNNs) and deployed on neuromorphic hardware platforms, including Intel Loihi 2, SpiNNaker2, and the BrainChip Akida accelerator. To quantify performance, we evaluate these algorithms against both synthetic and real-world datasets as well as compare against traditional RIID algorithms through GADRAS. The synthetic dataset was generated through PyRIID and consists of 25 isotopes across 124 shielding configurations, and the real-world dataset consists of roughly 200 test samples spanning 7 different isotopes of interest (133Ba, 226Ra, 235U, 232Th, 238U, 239Pu, 131I). We also measure energy efficiency of these algorithms through power profiling on the neuromorphic hardware. Significantly, our neuromorphic implementations consumed less than 1 mJ per inference, representing dramatic orders of magnitude reduction in energy consumption compared to traditional ARM-based GADRAS deployments. Our results also demonstrated the robustness of our developed LCA-based approach compared to a multi-layer perceptron ML model, which excelled on synthetic data and known noise models but failed to generalize to challenging real-world data. In contrast to the GADRAS baseline performance (F1 score) of 0.623, the ML-based model only achieved 0.466, whereas the LCA-based implementation was more closely matched at 0.579. Together, these findings underscore the potential of spiking neuromorphic hardware as a transformative technology for advancing RIID implementations, offering robust, energy-efficient, and field-deployable solutions for real-world applications such as real-time nuclear material detection.
- Open Access
- 8 August 2025
- Published by Wiley in Advanced Intelligent Systems
- Vol. 8 (1)
Is Computing with Light All You Need? A Perspective on Codesign for Optical Artificial Intelligence and Scientific Computing
Anything and everything can be solved with light—but under what contexts should one use optical computing and how should optical systems be designed for these tasks? In the shadow of reaching physical limits to traditional computer scaling and the large demands from artificial intelligence, research efforts have focused upon a range of optical computing pursuits as of late. This has included advances across a range of approaches, including free‐space and on‐chip implementations. Amid this excitement, key considerations beyond how to generally harness optical principles to enable computation, are what computations to advantageously pursue and how to design optical systems for these tasks. In particular, this perspective considers free‐space optical computing informed by recent research findings to consider select topics, including scene classification, integral differential equations, and many‐body simulations. In these contexts, this perspective considers what computations optical computing can and should enable and argues that a codesign approach whereby materials, devices, architectures, and algorithms are simultaneously optimized is needed considered for best performance.
- 8 August 2025
- Published by Wiley in Advanced Intelligent Systems
- Vol. 8 (1)
Open AccessIs Computing with Light All You Need? A Perspective on Codesign for Optical Artificial Intelligence and Scientific Computing
Anything and everything can be solved with light—but under what contexts should one use optical computing and how should optical systems be designed for these tasks? In the shadow of reaching physical limits to traditional computer scaling and the large demands from artificial intelligence, research efforts have focused upon a range of optical computing pursuits as of late. This has included advances across a range of approaches, including free‐space and on‐chip implementations. Amid this excitement, key considerations beyond how to generally harness optical principles to enable computation, are what computations to advantageously pursue and how to design optical systems for these tasks. In particular, this perspective considers free‐space optical computing informed by recent research findings to consider select topics, including scene classification, integral differential equations, and many‐body simulations. In these contexts, this perspective considers what computations optical computing can and should enable and argues that a codesign approach whereby materials, devices, architectures, and algorithms are simultaneously optimized is needed considered for best performance.
- Top Cited PapersOpen Access
- 11 February 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-24
The neurobench framework for benchmarking neuromorphic computing algorithms and systems
Neuromorphic computing shows promise for advancing computing efficiency and capabilities of AI applications using brain-inspired principles. However, the neuromorphic research field currently lacks standardized benchmarks, making it difficult to accurately measure technological advancements, compare performance with conventional methods, and identify promising future research directions. This article presents NeuroBench, a benchmark framework for neuromorphic algorithms and systems, which is collaboratively designed from an open community of researchers across industry and academia. NeuroBench introduces a common set of tools and systematic methodology for inclusive benchmark measurement, delivering an objective reference framework for quantifying neuromorphic approaches in both hardware-independent and hardware-dependent settings. For latest project updates, visit the project website (neurobench.ai).
- 11 February 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-24
Top Cited PapersOpen AccessThe neurobench framework for benchmarking neuromorphic computing algorithms and systems
Neuromorphic computing shows promise for advancing computing efficiency and capabilities of AI applications using brain-inspired principles. However, the neuromorphic research field currently lacks standardized benchmarks, making it difficult to accurately measure technological advancements, compare performance with conventional methods, and identify promising future research directions. This article presents NeuroBench, a benchmark framework for neuromorphic algorithms and systems, which is collaboratively designed from an open community of researchers across industry and academia. NeuroBench introduces a common set of tools and systematic methodology for inclusive benchmark measurement, delivering an objective reference framework for quantifying neuromorphic approaches in both hardware-independent and hardware-dependent settings. For latest project updates, visit the project website (neurobench.ai).
- Open Access
- 28 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Neuromorphic Population Evaluation using the Fugu Framework
- 28 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessNeuromorphic Population Evaluation using the Fugu Framework
- Open Access
- 28 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Context Modulation Enables Multi-tasking and Resource Efficiency in Liquid State Machines
- 28 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessContext Modulation Enables Multi-tasking and Resource Efficiency in Liquid State Machines
- 28 January 2019
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 1 (2) , 86-94
Training deep neural networks for binary communication with the Whetstone method
- 28 January 2019
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 1 (2) , 86-94
Training deep neural networks for binary communication with the Whetstone method