Search NASA⌕ Search

SEARCH · Search NASA

Results for “hardware neural networks”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities

Although deep learning has made great progress in recent years, the exploding economic and environmental costs of training neural networks are becoming unsustainable. To address this problem, there has been a great deal of research on algorithmically-efficient deep learning, which seeks to reduce training costs not at the hardware or implementation level, but through changes in the semantics of the training program. In this paper, we present a structured and comprehensive overview of the research in this field. First, we formalize the algorithmic speedup problem, then we use fundamental building blocks of algorithmically efficient training to develop a taxonomy. Our taxonomy highlights commonalities of seemingly disparate methods and reveals current research gaps. Next, we present evaluation best practices to enable comprehensive, fair, and reliable comparisons of speedup techniques. To further aid research and applications, we discuss common bottlenecks in the training pipeline (illustrated via experiments) and offer taxonomic mitigation strategies for them. Finally, we highlight some unsolved research challenges and present promising future directions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Bridging Python to Silicon: The SODA Toolchain

Systems performing scientific computing, data analysis, and machine learning tasks have a growing demand for application-specific accelerators that can provide high computational performance while meeting strict size and power requirements. However, the algorithms and applications that need to be accelerated are evolving at a rate that is incompatible with manual design processes based on hardware description languages. Agile hardware design tools based on compiler techniques can help by quickly producing an application-specific integrated circuit (ASIC) accelerator starting from a high-level algorithmic description. Here, we present the software-defined accelerator (SODA) synthesizer, a modular and open-source hardware compiler that provides automated end-to-end synthesis from high-level software frameworks to ASIC implementation, relying on multilevel representations to progressively lower and optimize the input code. Our approach does not require the application developer to write any register-transfer level code, and it is able to reach up to 364 giga floating point operations per second (GFLOPS)/W efficiency (32-bit precision) on typical convolutional neural network operators.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Biologically-informed excitatory and inhibitory ratio for robust spiking neural network training

Spiking neural networks drawing inspiration from biological constraints of the brain promise an energy-efficient paradigm for artificial intelligence. However, challenges exist in identifying guiding principles to train these networks in a robust fashion. In addition, training becomes an even more difficult problem when incorporating biological constraints of excitatory and inhibitory connections. In this work, we identify several key factors, such as low initial firing rates and diverse inhibitory spiking patterns, that determine the overall ability to train in the context of spiking networks with various ratios of excitatory to inhibitory neurons. The results indicate networks with biologically-realistic excitatory:inhibitory ratios can reliably train at low activity levels and in noisy environments. Additionally, the Van Rossum distance, a measure of spike train synchrony, provides insight into the importance of inhibitory neurons to increase network robustness to noise. This work supports further biologically-informed large-scale networks and energy efficient hardware implementations.

bio-inspired computing↗
DOE OSTI2020

Efficient I/O for Neural Network Training with Compressed Data

FanStore is a shared object store that enables efficient and scalable neural network training on supercomputers. By providing a global cache layer on node-local burst buffers using a compressed representation, it significantly enhances the processing capability of deep learning (DL) applications on existing hardware. In addition, FanStore allows POSIX-compliant file access to the compressed data in user space. We investigate the tradeoff between runtime overhead and data compression ratio using real-world datasets and applications, and propose a compressor selection algorithm to maximize storage capacity given performance constraints. We consider both asynchronous (i.e., with prefetching) and synchronous I/O strategies, and propose mechanisms for selecting compressors for both approaches. Using FanStore, the same storage hardware can host 2-13x more data for example applications without significant runtime overhead. Empirically, our experiments show that FanStore scales to 512 compute nodes with near linear performance scalability.

Zhang, Zhao↗
DOE OSTI2025

Evolution at the Edge: Real-Time Evolution for Neuromorphic Engine Control

Neuromorphic computing systems are attractive for real-time control at the edge because of their low power operation, real-time processing capabilities and their potential ability to do online learning. In this work, we describe an approach for performing real-time evolution of spiking neural networks for neuromorphic systems at the edge called Neuromorphic Optimization using Dynamic Evolutionary Systems or NODES. We apply this approach to real-time combustion engine control and develop an engine-specific hardware platform for NODES called FireBox. We demonstrate how the real-time evolution approach works in simulation and the performance of networks trained in simulation on the physical engine.

Maldonado Puente, Bryan [ORNL] (ORCID:000000033880↗
DOE OSTI2022

Lossy compression of statistical data using quantum annealer

Abstract We present a new lossy compression algorithm for statistical floating-point data through a representation learning with binary variables. The algorithm finds a set of basis vectors and their binary coefficients that precisely reconstruct the original data. The optimization for the basis vectors is performed classically, while binary coefficients are retrieved through both simulated and quantum annealing for comparison. A bias correction procedure is also presented to estimate and eliminate the error and bias introduced from the inexact reconstruction of the lossy compression for statistical data analyses. The compression algorithm is demonstrated on two different datasets of lattice quantum chromodynamics simulations. The results obtained using simulated annealing show 3–3.5 times better compression performance than the algorithm based on neural-network autoencoder. Calculations using quantum annealing also show promising results, but performance is limited by the integrated control error of the quantum processing unit, which yields large uncertainties in the biases and coupling parameters. Hardware comparison is further studied between the previous generation D-Wave 2000Q and the current D-Wave Advantage system. Our study shows that the Advantage system is more likely to obtain low-energy solutions for the problems than the 2000Q.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Neuro-Spark: A Submicrosecond Spiking Neural Networks Architecture for In-Sensor Filtering

Neuro-Spark, which is a new neuromorphic architecture with a field-programmable gate array (FPGA) implementation for ultrafast spiking neural network (SNN) inference at the edge, facilitates smart-pixel in-sensor filtering for high-energy physics experiments at the Large Hadron Collider (LHC). Utilizing the evolutionary optimization for neuromorphic systems (EONS) training method, we generate compact SNN models with 91% signal efficiency, akin to convolutional neural networks but with half the parameters. However, deploying near the detector poses a challenge because the SNN must handle a sustained input data rate exceeding 1013 GB/s. To overcome this, we propose a novel hardware architecture that uses high-level synthesis to construct a tuned architecture for the EONS-trained SNN. In addition to the analysis and validation with an AMD Xilinx Artix-A7 FPGA, our solution consumes only ç24% of FPGA LUT and flipflops. We also introduce an innovative quantization method that reduces FPGA resource utilization by ç15% without compromising accuracy. Our FPGA implementation achieves computing latency of ç10 ns for smart-pixel application inference on an edge FPGA.

Miniskar, Narasinga Rao↗
DOE OSTI2024

Impurity gas detection for SNF canisters using probabilistic deep learning and acoustic sensing *

Abstract Monitoring impurity gases in spent nuclear fuel (SNF) canisters is a novel structural health monitoring approach for SNF in dry storage. The SNF canisters are sealed containers that do not facilitate visual access to the inside. Acoustic sensing can be deployed by taking advantage of the pathways unobstructed by internal hardware. Although the ultrasonic time-of-flight measurement can provide valuable information, it is limited in its ability to discern the concentration of only one impurity gas. As such, deep learning algorithms, particularly convolutional neural networks (CNNs), offer a promising solution. In this study, CNN-based probabilistic deep learning models were implemented to detect and quantify multiple impurity gases in helium. An experimental platform was established to simulate canister conditions, and ultrasonic test data were collected. The presence of argon and air in helium at concentrations ranging from 0% to 1.2% at increments of 0.05% was considered. The multi-layer perceptron, decision tree, and logistic regression classifiers achieved high accuracies when distinguishing pure helium from helium with impurities. CNN with dropout layers and CNN using maximum likelihood estimation showed a similar performance, indicating their ability to capture uncertainties. The ensemble CNN model exhibited improved predictions and the ability to balance individual gas concentration by integrating 1D- and 2D-CNN models. These findings contribute probabilistic deep learning solutions for impurity gas detection and analysis within SNF canisters, thus ensuring safe storage and management of SNFs.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

BitGNN: Unlocking the Performance Potential of Binary Graph Neural Networks on GPUs

Graph Neural Networks (GNNs) have shown compelling results in many graph-based learning tasks. They are, however, time-consuming. Recent work has shown a promising direction in improving GNN speed and shrinking the size — network binarization, which binarizes network values and operations. Prior work, however, mainly focused on algorithm designs, leaving it open on how to fully materialize the performance potential. This work fills the gap by proposing techniques to best map binary GNNs and their computations to fit the nature of bit manipulations, optimizations and algorithms to maximize BSpMM kernel efficiency, and solutions to other factors influencing the end-to-end time on GPUs. Results on real-world graphs show that the proposed techniques outperform state of-the-art binary GNN implementations by 21-67× with little accuracy loss.

Chen, Jou-An↗
DOE OSTI2021

Boosting the signal-to-noise of low-field MRI with deep learning image reconstruction

Recent years have seen a resurgence of interest in inexpensive low magnetic field (< 0.3 T) MRI systems mainly due to advances in magnet, coil and gradient set designs. Most of these advances have focused on improving hardware and signal acquisition strategies, and far less on the use of advanced image reconstruction methods to improve attainable image quality at low field. We describe here the use of our end-to-end deep neural network approach (AUTOMAP) to improve the image quality of highly noise-corrupted low-field MRI data. We compare the performance of this approach to two additional state-of-the-art denoising pipelines. We find that AUTOMAP improves image reconstruction of data acquired on two very different low-field MRI systems: human brain data acquired at 6.5 mT, and plant root data acquired at 47 mT, demonstrating SNR gains above Fourier reconstruction by factors of 1.5- to 4.5-fold, and 3-fold, respectively. In these applications, AUTOMAP outperformed two different contemporary image-based denoising algorithms, and suppressed noise-like spike artifacts in the reconstructed images. The impact of domain-specific training corpora on the reconstruction performance is discussed. The AUTOMAP approach to image reconstruction will enable significant image quality improvements at low-field, especially in highly noise-corrupted environments.

42 ENGINEERING↗
DOE OSTI2022

Machine learning for continuous quantum error correction on superconducting qubits

Abstract Continuous quantum error correction has been found to have certain advantages over discrete quantum error correction, such as a reduction in hardware resources and the elimination of error mechanisms introduced by having entangling gates and ancilla qubits. We propose a machine learning algorithm for continuous quantum error correction that is based on the use of a recurrent neural network to identify bit-flip errors from continuous noisy syndrome measurements. The algorithm is designed to operate on measurement signals deviating from the ideal behavior in which the mean value corresponds to a code syndrome value and the measurement has white noise. We analyze continuous measurements taken from a superconducting architecture using three transmon qubits to identify three significant practical examples of non-ideal behavior, namely auto-correlation at temporal short lags, transient syndrome dynamics after each bit-flip, and drift in the steady-state syndrome values over the course of many experiments. Based on these real-world imperfections, we generate synthetic measurement signals from which to train the recurrent neural network, and then test its proficiency when implementing active error correction, comparing this with a traditional double threshold scheme and a discrete Bayesian classifier. The results show that our machine learning protocol is able to outperform the double threshold protocol across all tests, achieving a final state fidelity comparable to the discrete Bayesian classifier.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2025

Keeping LAMMPS cutting edge

Since its inception 30 years ago, LAMMPS has grown to be a world-class molecular dynamics code and a cornerstone of computational materials science research. This project aimed to keep LAMMPS at the forefront of molecular dynamics simulations by adapting LAMMPS to the latest developments in machine learning technology and hardware. Initially, the project set out to provide a unified implementation of active learning for efficient training data generation in LAMMPS, but the research trajectory pivoted to address more immediate and impactful opportunities. On the hardware side, recent record-breaking molecular dynamics simulations were developed on the Cerebras wafer-scale AI chip, and this project has developed an interface between LAMMPS and the hardware-specific molecular dynamics code to accelerate and simplify development and user adoption. On the software side, PyTorch’s Ahead-of-Time (AOT) compilation features promised increased performance for state-of-the-art equivariant neural network potentials, and this project laid the groundwork for their adoption in LAMMPS, resulting in a nearly 20x acceleration in extreme cases. Combined with a comprehensive benchmark study of LAMMPS across all current exascale systems, this project has reinforced LAMMPS’s role as a versatile, high-performance tool for current and future materials science applications.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Super Resolving Unrolled Neural Networks for Remote Sensing

In remote sensing systems, the capabilities of the system are constrained by the complex interactions between size, weight, and power (SWAP) of potential designs. In electro-optical (EO) systems, examples of these critical parameters include the system’s sensitivity and resolution. Those parameters can be increased by ever larger optical apertures and focal planes but at the cost of more SWAP. Multi-image super resolution (MISR) techniques allow resolution to be enhanced via computation rather than more sophisticated optical hardware. These algorithms combine multiple images together into a single, higher resolution image, trading temporal resolution and computation for spatial resolution. Fielded MISR techniques, such as Drizzle, can require several hundred images to create a single super resolved image, implying reduced temporal resolution, increased data acquisition load, and limiting mission applications. Iterative techniques, such as model-based image reconstruction and compressive sensing, have been shown to create super resolved images using fewer images than Drizzle. They do this by posing an optimization problem that balances accuracy between a highly accurate physical model and an image model. In the case of super resolution, the physical model is defined by the relation between low resolution input images and the desired high resolution output image. The image model encodes some assumptions about the super resolved image. These assumptions are meant to suppress reconstruction artifacts that arise due to deterministic physical model error, stochastic measurement noise, and potential undersampling. In practice, the performance of iterative methods are limited by imaging models compatible with optimization. Deep learning-based methods can effectively learn image models of arbitrary complexity, but lack the theoretical explainability and robustness of iterative techniques. Consensus equilibrium (CE) generalizes the iterative techniques beyond optimization, enabling blackbox algorithms such as traditional and neural image denoisers to be used as the image model. CE-based approaches retain much of the explainability and robustness of iterative techniques while allowing the expressiveness of machine learning image models to be used. Additionally, by unrolling iterations of CE with an embedded image denoiser, the image denoiser can be further trained and specialized to the specific application with potentially higher quality reconstructions. Under this project, we demonstrated the feasibility of training an unrolled neural network based upon CE. While we didn’t train one, we showed that the CE process is differentiable and its gradient can be tractably computed. We also explored the usage of a variants of CE akin to generative neural works. Most importantly, we applied the CE framework to a number of problems including non-blind deconvolution, upsampling, single-image super resolution, MISR, event-based sensing, and saturated deconvolution. Our MISR prototype creates high quality reconstructions with an order of magnitude fewer images than previous approaches and, critically, produces these reconstructions fast enough for practical usage.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

A hybrid neural architecture: Online attosecond x-ray characterization

The emergence of high-repetition-rate x-ray free-electron lasers (XFELs), such as SLAC’s LCLS-II, serves as our canonical example for autonomous controls that necessitate high-throughput diagnostics paired with streaming computational pipelines capable of single-shot analysis with extremely low latency. We present the deterministic characterization with an integrated parallelizable hybrid resolver architecture, a hybrid machine learning framework designed for fast, accurate analysis of XFEL diagnostics using angular streaking-based sinogram images. This architecture integrates convolutional neural networks and bidirectional long short-term memory models to denoise input, identify x-ray sub-spike features, and extract sub-spike relative delays with sub-30 attosecond temporal resolution. Deployed on low-latency hardware, it achieves over 10 kHz throughput with 168.3 μs inference latency, indicating scalability to 14 kHz with field-programmable gate array integration. By transforming regression tasks into classification problems and leveraging optimized error encoding, we achieve high precision with low-latency performance that is critical for real-time streaming event selection and experimental control feedback signals. This represents a key development in real-time control pipelines for next-generation autonomous science, generally, and high repetition-rate x-ray experiments in particular.

Accelerator Physics (physics.acc-ph)↗
DOE OSTI2021

Analysis and mitigation of parasitic resistance effects for analog in-memory neural network acceleration

To support the increasing demands for efficient deep neural network processing, accelerators based on analog in-memory computation of matrix multiplication have recently gained significant attention for reducing the energy of neural network inference. However, analog processing within memory arrays must contend with the issue of parasitic voltage drops across the metal interconnects, which distort the results of the computation and limit the array size. This work analyzes how parasitic resistance affects the end-to-end inference accuracy of state-of-the-art convolutional neural networks, and comprehensively studies how various design decisions at the device, circuit, architecture, and algorithm levels affect the system's sensitivity to parasitic resistance effects. Here, a set of guidelines are provided for how to design analog accelerator hardware that is intrinsically robust to parasitic resistance, without any explicit compensation or re-training of the network parameters.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Light-powered end-to-end neutron detection and imaging with an edge-deployed optical AI chip

Neutron detection is widely used in many applications including nuclear physics, nuclear energy, nuclear technologies and nuclear safeguards. Developing an end-to-end neutron detection and imaging workflow paves way towards fully automated processes for many applications. We implemented an automated workflow for neutron detection experiments which use a solid state image sensor to capture neutron hits as a digital image. We deploy the workflow to an edge-based optical neural network (ONN) to increase the radiation-hardness and lifetime of neutron detection instruments. We present a two-stage neural network framework for detection of neutrons at sub-pixel resolution. The first stage uses a region proposal network to efficiently detect and extract neutron hits from the input camera image. The second stage feeds the extracted hits into a fully connected neural network to predict the sub-pixel hit position. The performance of the two-stage framework is evaluated using the edge-based ONN. The results show that we can achieve above 96% neutron detection accuracy as well as sub-pixel and sub-micron position resolution, while enjoying the advantages of the ONN hardware including radiation-hardness, low energy consumption and high computing speed for integrated edge camera and hardware deployment, when compared with electronic counterparts.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Beyond 4D tracking: using cluster shapes for track seeding

Tracking is one of the most time consuming aspects of event reconstruction at the Large Hadron Collider (LHC) and its high-luminosity upgrade (HL-LHC). Innovative detector technologies extend tracking to four-dimensions by including timing in the pattern recognition and parameter estimation. However, present and future hardware already have additional information that is largely unused by existing track seeding algorithms. The shape of pixel-clusters provides an additional dimension for track seeding that can significantly reduce the combinatorial challenge of track finding. We use neural networks to show that cluster shapes can reduce significantly the rate of fake combinatorical backgrounds while preserving a high efficiency. We demonstrate this using the information in cluster singlets, doublets and triplets. Numerical results are presented with simulations from the TrackML challenge.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Exponential Escape Rate of Filamentary Incubation in Mott Spiking Neurons

Mott materials such as vanadium oxides, when subject to a strong applied voltage, present an inhomogeneous insulator-to-metal transition with formation of metallic filaments within the insulating bulk. This property is enabling the development of compact and power-efficient neuromorphic devices known as Mott neurons. However, the nature of the transition has not been fully understood yet, as it may be attributed to different effects, including Joule self-heating and hot-carrier injection. Moreover, the experimental determination of the threshold voltage needed to induce the transition has proven to be challenging, as the transition becomes increasingly unpredictable when the threshold is approached. The physical understanding of these issues would not only deepen our understanding of Mott insulators, but would also be an important step toward the realization of neuromorphic devices based on such materials. In this work we use numerical simulations based on the Mott resistor network model to study the nature of the filament incubation and formation process. Here, we show that both electronic and thermal effects, in the form of current density focusing and Joule self-heating, respectively, contribute to the filamentary incubation and growth. Remarkably, we find that the percolation of the metallic filaments near the threshold is intrinsically stochastic, qualitatively similar to the familiar Arrhenius activated behavior and to the stochastic firing of biological neurons. More precisely, we characterize the filament percolation as a Poisson point process, which has the same probability distribution as mathematical models of neuronal firing with an exponential escape rate. Finally, we support the numerical simulation results by performing experiments in VO 2 that are in agreement with the exponential escape rate behavior. Thus, we establish a functionality of Mott insulators that opens a path toward implementing neuromorphic hardware with quantum materials.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗