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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Real-time semantic segmentation on FPGAs for autonomous vehicles with hls4ml

In this paper, we investigate how field programmable gate arrays can serve as hardware accelerators for real-time semantic segmentation tasks relevant for autonomous driving. Considering compressed versions of the ENet convolutional neural network architecture, we demonstrate a fully-on-chip deployment with a latency of 4.9 ms per image, using less than 30% of the available resources on a Xilinx ZCU102 evaluation board. The latency is reduced to 3 ms per image when increasing the batch size to ten, corresponding to the use case where the autonomous vehicle receives inputs from multiple cameras simultaneously. We show, through aggressive filter reduction and heterogeneous quantization-aware training, and an optimized implementation of convolutional layers, that the power consumption and resource utilization can be significantly reduced while maintaining accuracy on the Cityscapes dataset.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

QuantumNAT: quantum noise-aware training with noise injection, quantization and normalization

Parameterized Quantum Circuits (PQC) are promising towards quantum advantage on near-term quantum hardware. However, due to the large quantum noises (errors), the performance of PQC models has a severe degradation on real quantum devices. Take Quantum Neural Network (QNN) as an example, the accuracy gap between noise-free simulation and noisy results on IBMQ-Yorktown for MNIST-4 classification is over 60%. Existing noise mitigation methods are general ones without leveraging unique characteristics of PQC; on the other hand, existing PQC work does not consider noise effect. To this end, we present QuantumNAT, a PQC-specific framework to perform noise-aware optimizations in both training and inference stages to improve robustness. We experimentally observe that the effect of quantum noise to PQC measurement outcome is a linear map from noise-free outcome with a scaling and a shift factor. Motivated by that, we propose post-measurement normalization to mitigate the feature distribution differences between noise-free and noisy scenarios. Furthermore, to improve the robustness against noise, we propose noise injection to the training process by inserting quantum error gates to PQC according to realistic noise models of quantum hardware. Lastly, post-measurement quantization is introduced to quantize the measurement outcomes to discrete values, achieving the denoising effect. Extensive experiments on 8 classification tasks using 6 quantum devices demonstrate that QuantumNAT improves accuracy by up to 43%, and achieves over 94% 2-class, 80% 4-class, and 34% 10-class classification accuracy measured on real quantum computers. The code for construction and noise-aware training of PQC is available in the TorchQuantum library.

Wang, Hanrui↗
DOE OSTI2024

Unifying Combinatorial and Graphical Methods in Artificial Intelligence

Recently, a new graph Laplacian, called the inner product Laplacian, was introduced which generalizes many existing Laplacians, including the normalized and combinatorial Laplacian and their weighted variants. The key observation behind the inner product Laplacian is that by defining appropriate inner product spaces on the vertices and edges, the standard Laplacians can be recovered as Hodge Laplacians over the simplicial complex formed by the edges and vertices. These inner product spaces form a natural way to incorporate non-combinatorial information into the definition of a domain-specific Laplacian. In particular, in contrast to current domain-specific weighting schemes which rely solely on edge weights, information regarding the similarity of non-adjacent vertices and arbitrary pairs of edges can be effectively incorporated into the Laplacian. In order to illustrate this approach we consider the problem of calculating the potential energy of an atomistic configuration using Graph Neural Networks. In comparison with start-of-the-art approaches, such as SchNet, our approach replaces a learned (via auto-encoder) representation of the atom types with an inner product space on atoms based on scientific knowledge (e.g., electronegativity). We will illustrate how this approach captures key chemical properties of the molecules and compare the energy calculations with state-of-the-art neural network approaches. However, to compute the resulting Laplacian involves a mixture of sparse and dense matrix computation and yields a dense matrix as the basis for the graph convolution. This dense convolutional kernel necessitates moving away from the standard message passing framework for graph neural networks and increases the computational cost of applying the kernel. In order to mitigate these costs we investigate means of leveraging the mixed sparse and dense computations to reduce the overall computational cost and how these approaches can be automatically transferred to energy efficient hardware (e.g., field programmable gate arrays (FPGAs)).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Ultrafast radiographic imaging and tracking: An overview of instruments, methods, data, and applications

Ultrafast radiographic imaging and tracking (U-RadIT) use state-of-the-art ionizing particle and light sources to experimentally study sub-nanosecond transients or dynamic processes in physics, chemistry, biology, geology, materials science and other fields. These processes are fundamental to modern technologies and applications, such as nuclear fusion energy, advanced manufacturing, communication, and green transportation, which often involve one mole or more atoms and elementary particles, and thus are challenging to compute by using the first principles of quantum physics or other forward models. One of the central problems in U-RadIT is to optimize information yield through, e.g. high-luminosity X-ray and particle sources, efficient imaging and tracking detectors, novel methods to collect data, and large-bandwidth online and offline data processing, regulated by the underlying physics, statistics, and computing power. We review and highlight recent progress in: (a.) Detectors such as high-speed complementary metal-oxide semiconductor (CMOS) cameras, hybrid pixelated array detectors integrated with Timepix4 and other application-specific integrated circuits (ASICs), and digital photon detectors; (b.) U-RadIT modalities such as dynamic phase contrast imaging, dynamic diffractive imaging, and four-dimensional (4D) particle tracking; (c.) U-RadIT data and algorithms such as neural networks and machine learning, and (d.) Applications in ultrafast dynamic material science using XFELs, synchrotrons and laser-driven sources. Hardware-centric approaches to U-RadIT optimization are constrained by detector material properties, low signal-to-noise ratio, high cost and long development cycles of critical hardware components such as ASICs. Interpretation of experimental data, including comparisons with forward models, is frequently hindered by sparse measurements, model and measurement uncertainties, and noise. Alternatively, U-RadIT make increasing use of data science and machine learning algorithms, including experimental implementations of compressed sensing. Machine learning and artificial intelligence approaches, refined by physics and materials information, may also contribute significantly to data interpretation, uncertainty quantification and U-RadIT optimization.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

MAD: Self-Supervised Masked Anomaly Detection Task for Multivariate Time Series

In this paper, we introduce Masked Anomaly Detection (MAD), a general self-supervised learning task for multivariate time series anomaly detection. With the increasing availability of sensor data from industrial systems, being able to detecting anomalies from streams of multivariate time series data is of significant importance. Given the scarcity of anomalies in real-world applications, the majority of literature has been focusing on modeling normality. The learned normal representations can empower anomaly detection as the model has learned to capture certain key underlying data regularities. A typical formulation is to learn a predictive model, i.e., use a window of time series data to predict future data values. In this paper, we propose an alternative self-supervised learning task. By randomly masking a portion of the inputs and training a model to estimate them using the remaining ones, MAD is an improvement over the traditional left-to-right next step prediction (NSP) task. Our experimental results demonstrate that MAD can achieve better anomaly detection rates over traditional NSP approaches when using exactly the same neural network (NN) base models, and can be modified to run as fast as NSP models during test time on the same hardware, thus making it an ideal upgrade for many existing NSP-based NN anomaly detection models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Multi-Objective Hyperparameter Optimization for Spiking Neural Network Neuroevolution

Neuroevolution has had significant success over recent years, but there has been relatively little work applying neuroevolution approaches to spiking neural networks (SNNs). SNNs are a type of neural network that includes temporal processing component, are not easily trained using other methods, and can be deployed into energy-efficient neuromorphic hardware. In this work, we investigate two evolutionary approaches for training SNNs. We explore the impact of the hyperparameters of the evolutionary approaches, including tournament size, population size, and representation type, on the performance of the algorithms. We present a multi-objective Bayesian-based hyperparameter optimization approach to tune the hyperparameters to produce the most accurate and smallest SNNs. We show that the hyperparameters can significantly affect the performance of these algorithms. We also perform sensitivity analysis and demonstrate that every hyperparameter value has the potential to perform well, assuming other hyperparameter values are set correctly.

Parsa, Maryam↗
DOE OSTI2020

Scaled-up Neuromorphic Array Communications Controller (SNACC) for Large-scale Neural Networks

Neuromorphic computing is one promising post-Moore’s law era technology, which takes inspiration from biological brains to perform computing tasks. The human brain contains billions of neurons with trillions of synapses and as neuromorphic hardware systems scale to larger and larger sizes, the communication system used to transfer information between neuromorphic elements and traditional computers must scale to keep up. In prior work, we describe the use of a separate neuromorphic array communications controller to support low-latency, high-throughput communication between our neuromorphic systems and a traditional computer. In this work, the neuromorphic array communications controller is used to support the scaling of a neuromorphic development system which uses multiple neuromorphic processors arranged in a two-dimensional array. The neuromorphic array communications controller, along with scalable local connections, is used to create a scalable neuromorphic platform to enable the development and testing of large neuromorphic network arrays.

Young, Aaron↗
DOE OSTI2025

End-to-End Workflow for Machine-Learning-Based Qubit Readout With QICK and hls4ml

In this article, we present an end-to-end workflow for superconducting qubit readout that embeds codesigned neural networks into the quantum instrumentation control kit (QICK). Capitalizing on the custom firmware and software of the QICK platform, which is built on Xilinx radiofrequency system-on-chip field-programmable gate arrays (FPGAs), we aim to leverage machine learning (ML) to address critical challenges in qubit readout accuracy and scalability. The workflow utilizes the hls4ml package and employs quantization-aware training to translate ML models into hardware-efficient FPGA implementations via user-friendly Python application programming interfaces. We experimentally demonstrate the design, optimization, and integration of an ML algorithm for single transmon qubit readout, achieving 96% single-shot fidelity with a latency of 32.25 ns and less than 16% FPGA lookup table resource utilization. Our results offer the community an accessible workflow to advance ML-driven readout and adaptive control in quantum information processing applications.

42 ENGINEERING↗
DOE OSTI2022

Neural network accelerator for quantum control

Efficient quantum control is necessary for practical quantum computing implementations with current technologies. Conventional algorithms for determining optimal control parameters are computationally expensive, largely excluding them from use outside of the simulation. Existing hardware solutions structured as lookup tables are imprecise and costly. By designing a machine learning model to approximate the results of traditional tools, a more efficient method can be produced. Such a model can then be synthesized into a hardware accelerator for use in quantum systems. In this study, we demonstrate a machine learning algorithm for predicting optimal pulse parameters. This algorithm is lightweight enough to fit on a low-resource FPGA and perform inference with a latency of 175 ns and pipeline interval of 5 ns with > 0.99 gate fidelity. In the long term, such an accelerator could be used near quantum computing hardware where traditional computers cannot operate, enabling quantum control at a reasonable cost at low latencies without incurring large data bandwidths outside of the cryogenic environment.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

Simplifying activations with linear approximations in neural networks

A key step in Neural Networks is activation. Among the different types of activation functions, sigmoid, tanh, and others involve the usage of exponents for calculation. From a hardware perspective, exponential implementation implies the usage of Taylor series or repeated methods involving many addition, multiplication, and division steps, and as a result are power-hungry and consume many clock cycles. We implement a piecewise linear approximation of the sigmoid function as a replacement for standard sigmoid activation libraries. This approach provides a practical alternative by leveraging piecewise segmentation, which simplifies hardware implementation and improves computational efficiency. In this paper, we detail piecewise functions that can be implemented using linear approximations and their implications for overall model accuracy and performance gain. Our results show that for the DenseNet, ResNet, and GoogLeNet architectures, the piecewise linear approximation of the sigmoid function provides faster execution times compared to the standard TensorFlow sigmoid implementation while maintaining comparable accuracy. Specifically, for MNIST with DenseNet, accuracy reaches 99.91% (Piecewise) vs. 99.97% (Base) with up to 1.31x speedup in execution time. For CIFAR-10 with DenseNet, accuracy improves to 98.97% (Piecewise) vs. 99.40% (Base) while achieving 1.24x faster execution. Similarly, for CIFAR-100 with DenseNet, the accuracy is 97.93% (Piecewise) vs. 98.39% (Base), with a 1.18x execution time reduction. These results confirm the proposed method’s capability to efficiently process large-scale datasets and computationally demanding tasks, offering a practical means to accelerate deep learning models, including LSTMs, without compromising accuracy.

Activation function↗
DOE OSTI2020

Real-time optimization of multi-cell industrial evaporative cooling towers using machine learning and particle swarm optimization

Existing electrical generating stations must operate with greater flexibility due to increasing renewable energy penetration on the electrical grid, and many coal-fired power stations have transitioned away from baseload operation to load-following operation to aid in grid stability. In cases where multiple independently controlled cooling tower cells are used in parallel for the cooling purposes of such stations, there is an opportunity to increase plant efficiency through data-driven optimization across their full load ranges. This work presents a novel application of real-time optimization using machine learning and particle swarm optimization on a multi-cell induced-draft cooling tower servicing a coal-fired power station under variable load. This is the first work to demonstrate simultaneous optimization of a multi-cell cooling tower, in addition to using machine learning for closed-loop control on a cooling tower. A novel control configuration is presented that ensures original control logic is not adversely affected and that the overall plant process is not disrupted using only existing hardware and operational data. To verify this methodology, the 12 independent cooling tower cells are simulated in parallel using historic operating data to demonstrate the effectiveness of real-time optimization compared to current practice. An artificial neural network is trained to predict overall cooling tower power consumption using only operational data and ambient conditions with an R2 value of greater than 0.96. The real-time optimization using particle swarm yields 6.7% annual energy usage savings compared to current practices, although the extent of the real-time savings varies greatly with both plant load and environmental conditions. This is particularly significant for a variable load situation because frequent ramping typically results in reduced overall efficiency. Furthermore, this proposed AI-based solution presents an opportunity to improve the overall heat rate of a load-following coal-fired power plant without the need to perform extensive first-principles modeling or add additional hardware to the cooling tower, resulting in more resources conserved and less overall emissions per unit of electricity generated.

42 ENGINEERING↗
DOE OSTI2025

Surrogate Neural Architecture Codesign Package (SNAC-Pack)

Neural Architecture Search is a powerful approach for automating model design, but existing methods struggle to accurately optimize for real hardware performance, often relying on proxy metrics such as bit operations. We present Surrogate Neural Architecture Codesign Package (SNAC-Pack), an integrated framework that automates the discovery and optimization of neural networks focusing on FPGA deployment. SNAC-Pack combines Neural Architecture Codesign's multi-stage search capabilities with the Resource Utilization and Latency Estimator, enabling multi-objective optimization across accuracy, FPGA resource utilization, and latency without requiring time-intensive synthesis for each candidate model. We demonstrate SNAC-Pack on a high energy physics jet classification task, achieving 63.84% accuracy with resource estimation. When synthesized on a Xilinx Virtex UltraScale+ VU13P FPGA, the SNAC-Pack model matches baseline accuracy while maintaining comparable resource utilization to models optimized using traditional BOPs metrics. This work demonstrates the potential of hardware-aware neural architecture search for resource-constrained deployments and provides an open-source framework for automating the design of efficient FPGA-accelerated models.

Weitz, Jason [UC, San Diego] (ORCID:00090004631535↗
DOE OSTI2022

A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipelining

Transformers are considered one of the most important deep learning models since 2018, in part because it establishes state-of-the-art (SOTA) records and could potentially replace existing Deep Neural Networks (DNNs). Despite the remarkable triumphs, the prolonged turnaround time of Transformer models is a widely recognized roadblock. The variety of sequence lengths imposes additional computing overhead where inputs need to be zero-padded to the maximum sentence length in the batch to accommodate the parallel computing platforms. This paper targets the field-programmable gate array (FPGA) and proposes a coherent sequence length adaptive algorithm–hardware co-design for Transformer acceleration. Particularly, we develop a hardware-friendly sparse attention operator and a length-aware hardware resource scheduling algorithm. The proposed sparse attention operator brings the complexity of attention-based models down to linear complexity and alleviates the off-chip memory traffic. The proposed length-aware resource hardware scheduling algorithm dynamically allocates the hardware resources to fill up the pipeline slots and eliminates bubbles for NLP tasks. Experiments show that our design has very small accuracy loss and has 80.2 × and 2.6 × speedup compared to CPU and GPU implementation, and 4 × higher energy efficiency than state-of-the-art GPU accelerator optimized via CUBLAS GEMM.

Peng, Hongwu↗
DOE OSTI2022

A workflow for segmenting soil and plant X-ray computed tomography images with deep learning in Google’s Colaboratory

X-ray micro-computed tomography (X-ray μCT) has enabled the characterization of the properties and processes that take place in plants and soils at the micron scale. Despite the widespread use of this advanced technique, major limitations in both hardware and software limit the speed and accuracy of image processing and data analysis. Recent advances in machine learning, specifically the application of convolutional neural networks to image analysis, have enabled rapid and accurate segmentation of image data. Yet, challenges remain in applying convolutional neural networks to the analysis of environmentally and agriculturally relevant images. Specifically, there is a disconnect between the computer scientists and engineers, who build these AI/ML tools, and the potential end users in agricultural research, who may be unsure of how to apply these tools in their work. Additionally, the computing resources required for training and applying deep learning models are unique, more common to computer gaming systems or graphics design work, than to traditional computational systems. To navigate these challenges, we developed a modular workflow for applying convolutional neural networks to X-ray μCT images, using low-cost resources in Google’s Colaboratory web application. Here we present the results of the workflow, illustrating how parameters can be optimized to achieve best results using example scans from walnut leaves, almond flower buds, and a soil aggregate. We expect that this framework will accelerate the adoption and use of emerging deep learning techniques within the plant and soil sciences.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Object Detection and Recognition with PointPillars in LiDAR Point Clouds – Comparisions

In the field of autonomous systems, neural networks have been leveraged for object detection and recognition in 2-dimensional images captured by cameras. Other types of sensors are available for sensing surroundings, including LiDAR sensors, and corresponding networks have been developed to perform detection and recognition in the point clouds generated by these sensors. The approaches are similar, both perform convolutions, but have distinct characteristics and challenges. In designing and configuring autonomous systems, a variety of LiDAR sensors are available, along with configurable deep neural networks to leverage their data. This work presents a review of the PointPillars network, an evolution of the seminal PointNet, comparing accuracy and training time relative to different LiDAR sensors, network and training parameters, CPU and GPU hardware, and the criticality of the use of reflective intensity as a feature. The value of using reflectivity as a predictive feature is explored and quantified to determine if it makes a significant difference in accuracy of the PointPillars network. Two separate LiDAR sensors are utilized, a 16-plane and a 32-plane, and corresponding accuracies and training times with the PointPillars network are evaluated.

LiDAR, machine learning, neural network, object re↗
DOE OSTI2023

FAIR AI models in high energy physics

Abstract The findable, accessible, interoperable, and reusable (FAIR) data principles provide a framework for examining, evaluating, and improving how data is shared to facilitate scientific discovery. Generalizing these principles to research software and other digital products is an active area of research. Machine learning models—algorithms that have been trained on data without being explicitly programmed—and more generally, artificial intelligence (AI) models, are an important target for this because of the ever-increasing pace with which AI is transforming scientific domains, such as experimental high energy physics (HEP). In this paper, we propose a practical definition of FAIR principles for AI models in HEP and describe a template for the application of these principles. We demonstrate the template’s use with an example AI model applied to HEP, in which a graph neural network is used to identify Higgs bosons decaying to two bottom quarks. We report on the robustness of this FAIR AI model, its portability across hardware architectures and software frameworks, and its interpretability.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

Toward Large-Scale Image Segmentation on Summit

Semantic segmentation of images is an important computer vision task that emerges in a variety of application domains such as medical imaging, robotic vision and autonomous vehicles to name a few. While these domain-specific image analysis tasks involve relatively small image sizes (~ 10 2 × 10 2 ), there are many applications that need to train machine learning models on image data with extents that are orders of magnitude larger (~10 4 × 10 4 ). Training deep neural network (DNN) models on large extent images is extremely memory-intensive and often exceeds the memory limitations of a single graphical processing unit, a hardware accelerator of choice for computer vision workloads. Here, an efficient, sample parallel approach to train U-Net models on large extent image data sets is presented. Its advantages and limitations are analyzed and near-linear strong-scaling speedup demonstrated on 256 nodes (1536 GPUs) of the Summit supercomputer. Using a single node of the Summit supercomputer, an early evaluation of a recently released model parallel framework called GPipe is demonstrated to deliver ~ 2X speedup in executing a U-Net model with an order of magnitude larger number of trainable parameters than reported before. Performance bottlenecks for pipelined training of U-Net models are identified and mitigation strategies to improve the speedups are discussed. Together, these results open up the possibility of combining both approaches into a unified scalable pipelined and data parallel algorithm to efficiently train U-Net models with very large receptive fields on data sets of ultra-large extent images.

Seal, Sudip↗
DOE OSTI2026

Advancing Industry 4.0: Multimodal Sensor Fusion for AI-Based Fault Detection in 3D Printing

Additive manufacturing, particularly fused deposition modeling, is transforming modern production by enabling rapid prototyping and complex part fabrication. However, its layer-by-layer process remains vulnerable to faults such as nozzle clogging, filament runout, and layer misalignment, which compromise print quality and reliability. Traditional inspection methods are costly, time-intensive, and often limited to post-process analysis, making them unsuitable for real-time intervention. In this current study, the authors developed a novel, low-cost, and portable faultdetection system that leverages multimodal sensor fusion and artificial intelligence for real-time monitoring in FDM-based 3D printing. The system integrates acoustic, vibration, and thermal sensing into a non-intrusive architecture, capturing complementary data streams that reflect both mechanical and process-related anomalies. Acoustic and thermal sensors operate in a fully contactless manner, while the vibration sensor requires minimal attachment such that it will not interfere with printer hardware, thereby preserving portability and ease of deployment. The multimodal signals are processed into spectrograms and time-frequency features, which are classified using convolutional neural networks for intelligent fault detection. The proposed system advances Industry 4.0 objectives by offering an affordable, scalable, and practical monitoring solution that improves faultdetection accuracy, reduces waste, and supports sustainable, adaptive manufacturing.

42 ENGINEERING↗