Garrett T. Kenyon
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
Research Subjects
Garrett T. Kenyon has a total of 197 co-authors. Here are the top co-authors by number of shared publications:
Steven P. Brumby
Los Alamos National Lab. (United States)
9 shared publicationsShawn Barr
7 shared publicationsJohn S. George
6 shared publicationsLuis M. A. Bettencourt
Santa Fe Institute, USA
6 shared publicationsJohn George
Los Alamos National Laboratory, Los Alamos, New Mexico, USA
5 shared publicationsZhengping Ji
Los Alamos National Lab. (United States)
5 shared publications
Latest Publications
- Open Access
- 4 June 2025
- Published by Springer Nature in npj Unconventional Computing
- Vol. 2 (1) , 1-12
Comparing quantum annealing and spiking neuromorphic computing for sampling binary sparse coding QUBO problems
We consider the problem of computing a sparse binary representation of an image. Given an image and an overcomplete, non-orthonormal basis, we aim to find a sparse binary vector indicating the minimal set of basis vectors that when added together best reconstruct the given input. We formulate this problem with an L 2 loss on the reconstruction error, and an L 0 loss on the binary vector enforcing sparsity. First, we solve the sparse representation QUBOs by solving them both on a D-Wave quantum annealer with Pegasus chip connectivity, as well as on the Intel Loihi 2 spiking neuromorphic processor using a stochastic Non-equilibrium Boltzmann Machine (NEBM). Second, using Quantum Evolution Monte Carlo with Reverse Annealing and iterated warm starting on Loihi 2 to evolve the solution quality from the respective machines. We demonstrate that both quantum annealing and neuromorphic computing are suitable for solving binary sparse coding QUBOs.
- 4 June 2025
- Published by Springer Nature in npj Unconventional Computing
- Vol. 2 (1) , 1-12
Open AccessComparing quantum annealing and spiking neuromorphic computing for sampling binary sparse coding QUBO problems
We consider the problem of computing a sparse binary representation of an image. Given an image and an overcomplete, non-orthonormal basis, we aim to find a sparse binary vector indicating the minimal set of basis vectors that when added together best reconstruct the given input. We formulate this problem with an L 2 loss on the reconstruction error, and an L 0 loss on the binary vector enforcing sparsity. First, we solve the sparse representation QUBOs by solving them both on a D-Wave quantum annealer with Pegasus chip connectivity, as well as on the Intel Loihi 2 spiking neuromorphic processor using a stochastic Non-equilibrium Boltzmann Machine (NEBM). Second, using Quantum Evolution Monte Carlo with Reverse Annealing and iterated warm starting on Loihi 2 to evolve the solution quality from the respective machines. We demonstrate that both quantum annealing and neuromorphic computing are suitable for solving binary sparse coding QUBOs.
- Open Access
Demonstrating the Suitability of Neuromorphic, Event-Based, Dynamic Vision Sensors for In Process Monitoring of Metallic Additive Manufacturing and Welding
We demonstrate the suitability of high dynamic range, high-speed, neuromorphic event-based, dynamic vision sensors for metallic additive manufacturing and welding for in-process monitoring applications. In-process monitoring to enable quality control of mission critical components produced using metallic additive manufacturing is of high interest. However, the extreme light environment and high speed dynamics of metallic melt pools have made this a difficult environment in which to make measurements. Event-based sensing is an alternative measurement paradigm where data is only transmitted/recorded when a measured quantity exceeds a threshold resolution. The result is that event-based sensors consume less power and less memory/bandwidth, and they operate across a wide range of timescales and dynamic ranges. Event-driven driven imagers stand out from conventional imager technology in that they have a very high dynamic range of approximately 120 dB. Conventional 8 bit imagers only have a dynamic range of about 48 dB. This high dynamic range makes them a good candidate for monitoring manufacturing processes that feature high intensity light sources/generation such as metallic additive manufacturing and welding. In addition event based imagers are able to capture data at timescales on the order of 100 μs, which makes them attractive to capturing fast dynamics in a metallic melt pool. In this work we demonstrate that event-driven imagers have been shown to be able to observe tungsten inert gas (TIG) and laser welding melt pools. The results of this effort suggest that with additional engineering effort, neuromorphic event imagers should be capable of 3D geometry measurements of the melt pool, and anomaly detection/classification/prediction.
Open AccessDemonstrating the Suitability of Neuromorphic, Event-Based, Dynamic Vision Sensors for In Process Monitoring of Metallic Additive Manufacturing and Welding
We demonstrate the suitability of high dynamic range, high-speed, neuromorphic event-based, dynamic vision sensors for metallic additive manufacturing and welding for in-process monitoring applications. In-process monitoring to enable quality control of mission critical components produced using metallic additive manufacturing is of high interest. However, the extreme light environment and high speed dynamics of metallic melt pools have made this a difficult environment in which to make measurements. Event-based sensing is an alternative measurement paradigm where data is only transmitted/recorded when a measured quantity exceeds a threshold resolution. The result is that event-based sensors consume less power and less memory/bandwidth, and they operate across a wide range of timescales and dynamic ranges. Event-driven driven imagers stand out from conventional imager technology in that they have a very high dynamic range of approximately 120 dB. Conventional 8 bit imagers only have a dynamic range of about 48 dB. This high dynamic range makes them a good candidate for monitoring manufacturing processes that feature high intensity light sources/generation such as metallic additive manufacturing and welding. In addition event based imagers are able to capture data at timescales on the order of 100 μs, which makes them attractive to capturing fast dynamics in a metallic melt pool. In this work we demonstrate that event-driven imagers have been shown to be able to observe tungsten inert gas (TIG) and laser welding melt pools. The results of this effort suggest that with additional engineering effort, neuromorphic event imagers should be capable of 3D geometry measurements of the melt pool, and anomaly detection/classification/prediction.
- Open Access
- 12 September 2024
- Published by Office of Scientific and Technical Information (OSTI)
Using Neuromorphic Processors to Model Biological Neural Processing: Synthetic Cognition in a Neuromorphic Agent?
The U.S. Department of Energy's Office of Scientific and Technical Information
- 12 September 2024
- Published by Office of Scientific and Technical Information (OSTI)
Open AccessUsing Neuromorphic Processors to Model Biological Neural Processing: Synthetic Cognition in a Neuromorphic Agent?
The U.S. Department of Energy's Office of Scientific and Technical Information
- Open Access
How Robust Are Energy-Based Models Trained With Equilibrium Propagation?
Deep neural networks (DNNs) are easily fooled by adversarial perturbations that are imperceptible to humans. Adversarial training, a process where adversarial examples are added to the training set, is the current state-of-the-art defense against adversarial attacks, but it lowers the model's accuracy on clean inputs, is computationally expensive, and offers less robustness to natural noise. In contrast, energy-based models (EBMs), which were designed for efficient implementation in neuromorphic hardware and physical systems, incorporate feedback connections from each layer to the previous layer, yielding a recurrent, deep-attractor architecture which we hypothesize should make them naturally robust. Our work is the first to explore the robustness of EBMs to both natural corruptions and adversarial attacks, which we do using the CIFAR-10 and CIFAR-100 datasets. We demonstrate that EBMs are more robust than transformers and display comparable robustness to adversarially-trained DNNs on gradient-based (white-box) attacks, query-based (black-box) attacks, and natural perturbations without sacrificing clean accuracy, and without the need for adversarial training or additional training techniques.
Open AccessHow Robust Are Energy-Based Models Trained With Equilibrium Propagation?
Deep neural networks (DNNs) are easily fooled by adversarial perturbations that are imperceptible to humans. Adversarial training, a process where adversarial examples are added to the training set, is the current state-of-the-art defense against adversarial attacks, but it lowers the model's accuracy on clean inputs, is computationally expensive, and offers less robustness to natural noise. In contrast, energy-based models (EBMs), which were designed for efficient implementation in neuromorphic hardware and physical systems, incorporate feedback connections from each layer to the previous layer, yielding a recurrent, deep-attractor architecture which we hypothesize should make them naturally robust. Our work is the first to explore the robustness of EBMs to both natural corruptions and adversarial attacks, which we do using the CIFAR-10 and CIFAR-100 datasets. We demonstrate that EBMs are more robust than transformers and display comparable robustness to adversarially-trained DNNs on gradient-based (white-box) attacks, query-based (black-box) attacks, and natural perturbations without sacrificing clean accuracy, and without the need for adversarial training or additional training techniques.
- Open Access
- 28 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Implementing and Benchmarking the Locally Competitive Algorithm on the Loihi 2 Neuromorphic Processor
- 28 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessImplementing and Benchmarking the Locally Competitive Algorithm on the Loihi 2 Neuromorphic Processor
- Open Access
- 28 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Sampling binary sparse coding QUBO models using a spiking neuromorphic processor
We consider the problem of computing a sparse binary representation of an image. To be precise, given an image and an overcomplete, non-orthonormal basis, we aim to find a sparse binary vector indicating the minimal set of basis vectors that when added together best reconstruct the given input. We formulate this problem with an L2 loss on the reconstruction error, and an L0 (or, equivalently, an L1) loss on the binary vector enforcing sparsity. This yields a so-called Quadratic Unconstrained Binary Optimization (QUBO) problem, whose solution is generally NP-hard to find. The contribution of this work is twofold. First, the method of unsupervised and unnormalized dictionary feature learning for a desired sparsity level to best match the data is presented. Second, the binary sparse coding problem is then solved on the Loihi 1 neuromorphic chip by the use of stochastic networks of neurons to traverse the non-convex energy landscape. The solutions are benchmarked against the classical heuristic simulated annealing. We demonstrate neuromorphic computing is suitable for sampling low energy solutions of binary sparse coding QUBO models, and although Loihi 1 is capable of sampling very sparse solutions of the QUBO models, there needs to be improvement in the implementation in order to be competitive with simulated annealing.
- 28 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessSampling binary sparse coding QUBO models using a spiking neuromorphic processor
We consider the problem of computing a sparse binary representation of an image. To be precise, given an image and an overcomplete, non-orthonormal basis, we aim to find a sparse binary vector indicating the minimal set of basis vectors that when added together best reconstruct the given input. We formulate this problem with an L2 loss on the reconstruction error, and an L0 (or, equivalently, an L1) loss on the binary vector enforcing sparsity. This yields a so-called Quadratic Unconstrained Binary Optimization (QUBO) problem, whose solution is generally NP-hard to find. The contribution of this work is twofold. First, the method of unsupervised and unnormalized dictionary feature learning for a desired sparsity level to best match the data is presented. Second, the binary sparse coding problem is then solved on the Loihi 1 neuromorphic chip by the use of stochastic networks of neurons to traverse the non-convex energy landscape. The solutions are benchmarked against the classical heuristic simulated annealing. We demonstrate neuromorphic computing is suitable for sampling low energy solutions of binary sparse coding QUBO models, and although Loihi 1 is capable of sampling very sparse solutions of the QUBO models, there needs to be improvement in the implementation in order to be competitive with simulated annealing.
- Open Access
Sampling binary sparse coding QUBO models using a spiking neuromorphic processor
We consider the problem of computing a sparse binary representation of an image. To be precise, given an image and an overcomplete, non-orthonormal basis, we aim to find a sparse binary vector indicating the minimal set of basis vectors that when added together best reconstruct the given input. We formulate this problem with an $L_2$ loss on the reconstruction error, and an $L_0$ (or, equivalently, an $L_1$) loss on the binary vector enforcing sparsity. This yields a so-called Quadratic Unconstrained Binary Optimization (QUBO) problem, whose solution is generally NP-hard to find. The contribution of this work is twofold. First, the method of unsupervised and unnormalized dictionary feature learning for a desired sparsity level to best match the data is presented. Second, the binary sparse coding problem is then solved on the Loihi 1 neuromorphic chip by the use of stochastic networks of neurons to traverse the non-convex energy landscape. The solutions are benchmarked against the classical heuristic simulated annealing. We demonstrate neuromorphic computing is suitable for sampling low energy solutions of binary sparse coding QUBO models, and although Loihi 1 is capable of sampling very sparse solutions of the QUBO models, there needs to be improvement in the implementation in order to be competitive with simulated annealing.Open AccessSampling binary sparse coding QUBO models using a spiking neuromorphic processor
We consider the problem of computing a sparse binary representation of an image. To be precise, given an image and an overcomplete, non-orthonormal basis, we aim to find a sparse binary vector indicating the minimal set of basis vectors that when added together best reconstruct the given input. We formulate this problem with an $L_2$ loss on the reconstruction error, and an $L_0$ (or, equivalently, an $L_1$) loss on the binary vector enforcing sparsity. This yields a so-called Quadratic Unconstrained Binary Optimization (QUBO) problem, whose solution is generally NP-hard to find. The contribution of this work is twofold. First, the method of unsupervised and unnormalized dictionary feature learning for a desired sparsity level to best match the data is presented. Second, the binary sparse coding problem is then solved on the Loihi 1 neuromorphic chip by the use of stochastic networks of neurons to traverse the non-convex energy landscape. The solutions are benchmarked against the classical heuristic simulated annealing. We demonstrate neuromorphic computing is suitable for sampling low energy solutions of binary sparse coding QUBO models, and although Loihi 1 is capable of sampling very sparse solutions of the QUBO models, there needs to be improvement in the implementation in order to be competitive with simulated annealing. - Open Access
- 11 August 2022
- Published by Office of Scientific and Technical Information (OSTI)
Sparse Coding for Depth Completion on Autonomous Vehicles [Slides]
The U.S. Department of Energy's Office of Scientific and Technical Information
- 11 August 2022
- Published by Office of Scientific and Technical Information (OSTI)
Open AccessSparse Coding for Depth Completion on Autonomous Vehicles [Slides]
The U.S. Department of Energy's Office of Scientific and Technical Information
- 16 May 2022
- Published by Office of Scientific and Technical Information (OSTI)
Sparse coding algorithm on a quantum annealer for arbitrarily large problems [Slides]
The U.S. Department of Energy's Office of Scientific and Technical Information
- 16 May 2022
- Published by Office of Scientific and Technical Information (OSTI)
Sparse coding algorithm on a quantum annealer for arbitrarily large problems [Slides]
The U.S. Department of Energy's Office of Scientific and Technical Information