Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning efficiency”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

DECAL MDN Resolution Calibration

The simulated pixelated calorimeter uses 0.1 mm × 0.1 mm silicon pixels (0.0001 cm²) silicon pixels as active layers — far finer than current concepts like HGCAL (~0.5 cm²) — improving energy resolution through much finer segmentation. While the standard resolution formalism fits three numbers to a handful of discrete test-beam energies, this work is a first try at a more data-efficient alternative: learning the full response shape continuously in energy with a mixture density network. This continuous, differentiable surrogate is a natural building block for fast simulation of extremely complex calorimeters.

Wang, Peter [U. Chicago (main)]↗
DOE OSTI2025

Rapid Inference of Logic Gate Neural Networks for Anomaly Detection in High Energy Physics

The increasing data rates and complexity of detectors at the Large Hadron Collider (LHC) necessitate fast and efficient machine learning models, particularly for rapid selection of what data to store, known as triggering. Building on recent work in differentiable logic gates, we present a public implementation of a Convolutional Differentiable Logic Gate Neural Network (CLGN). We apply this to detecting anomalies at the Level-1 Trigger at CMS using public data from the CICADA project. We demonstrate that the CLGN achieves physics performance on par with or superior to conventional quantized neural networks. We also synthesize an LGN for a Field-Programmable Gate Array (FPGA) and show highly promising FPGA characteristics, notably zero Digital Signal Processor (DSP) resource usage. This work highlights the potential of logic gate networks for high-speed, on-detector inference in High Energy Physics and beyond.

FOS: Physical sciences↗
NASA NTRS1997

Efficiently Ranking Hyphotheses in Machine Learning

This paper considers the problem of learning the ranking of a set of alternatives based upon incomplete information (e.g. a limited number of observations). At each decision cycle, the system can output a complete ordering on the hypotheses or decide to gather additional information (e.g. observation) at some cost.

Machine Learning algorithm parametric ranking↗
NASA NTRS2011

Volumetric 3D Display System with Static Screen

Current display technology has relied on flat, 2D screens that cannot truly convey the third dimension of visual information: depth. In contrast to conventional visualization that is primarily based on 2D flat screens, the volumetric 3D display possesses a true 3D display volume, and places physically each 3D voxel in displayed 3D images at the true 3D (x,y,z) spatial position. Each voxel, analogous to a pixel in a 2D image, emits light from that position to form a real 3D image in the eyes of the viewers. Such true volumetric 3D display technology provides both physiological (accommodation, convergence, binocular disparity, and motion parallax) and psychological (image size, linear perspective, shading, brightness, etc.) depth cues to human visual systems to help in the perception of 3D objects. In a volumetric 3D display, viewers can watch the displayed 3D images from a completely 360 view without using any special eyewear. The volumetric 3D display techniques may lead to a quantum leap in information display technology and can dramatically change the ways humans interact with computers, which can lead to significant improvements in the efficiency of learning and knowledge management processes. Within a block of glass, a large amount of tiny dots of voxels are created by using a recently available machining technique called laser subsurface engraving (LSE). The LSE is able to produce tiny physical crack points (as small as 0.05 mm in diameter) at any (x,y,z) location within the cube of transparent material. The crack dots, when illuminated by a light source, scatter the light around and form visible voxels within the 3D volume. The locations of these tiny voxels are strategically determined such that each can be illuminated by a light ray from a high-resolution digital mirror device (DMD) light engine. The distribution of these voxels occupies the full display volume within the static 3D glass screen. This design eliminates any moving screen seen in previous approaches, so there is no image jitter, and has an inherent parallel mechanism for 3D voxel addressing. High spatial resolution is possible with a full color display being easy to implement. The system is low-cost and low-maintenance.

Geng, Jason↗
NASA NTRSDate not supplied

A Framework for Software Health Management Using Bayesian Statistics

Software Health Management (SWHM) must make sure that the software always remains in safe and healthy regions of the state space. Boundaries between healthy and unhealthy regions are important for the detection of violations and health management.In this position paper, we present a framework, which employs techniques from Bayesian statistical modeling and active learning to efficiently characterize health boundaries in high-dimensional spaces. We will discuss, how this framework supports SWHM during design time and during operation of learning/adapting software systems

software health management↗
NASA NTRSDate not supplied

Operational Implications from Field Test Results: Sensorimotor Guidelines for Exploration Missions

Two key sensorimotor objectives of the joint NASA-Russian Field Test (FT) study were (1) to quantify functional performance on long duration crewmembers as close to landing as possible, and (2) to develop a recovery timeline back to preflight baseline. The purpose of this presentation is to provide an overview of the FT results and discuss the operational implications for future exploration missions. The NASA and Russian teams conducted a total of 48 Field Tests, including 18 using a reduced Pilot FT (PFT) protocol. The combined PFT/FT cohort included 14 first-time fliers, 4F, and nine cosmonauts who repeated FT during a second mission. The mission durations were 185 ± 42 days, mean ± std. Nominally, the initial postflight session was performed in the medical test at the Soyuz landing site or at the nearby airport (R+2.2 ± 1.3 hrs, mean ± std), and then repeated multiple times throughout the postflight recovery. The common tasks performed across PFT and full FT protocols included sit-to-stand, recovery from fall (prone to stand) and tandem walk, performed in that order of increasing difficulty. The full FT protocol also included seated tasks (eccentric gaze, dysmetria finger to nose, eye-hand coordination on a tablet, grip force discrimination), a standing posture test with an upper body perturbation, a timed up and go mobility test with obstacles, and a dynamic visual acuity task during vertical oscillations. While there was considerable variability in the postflight outcome measures across crewmembers, the level of vestibular/cerebellar and sensorimotor impairment was greater than previously observed during shorter spaceflight missions. Most striking was the higher incidence of motion sickness even without constraining the standard medical interventions. Motion sensitivity prevented some crewmembers from attempting and/or completing the early testing. The recovery timeline varied with task complexity, generally taking longer when either the basis of support was limited (e.g., tandem walk) or visual cues were deprived (eyes closed). Based on this evidence, mission planners need to expect a range of response across individuals and tasks following G-transitions. Individual health assessments are recommended along with development of pre-worked, prioritized content and timelines, with the ability to change roles depending on crew readiness. Handholds and balance aids are recommended to help stabilize the crewmembers to perform specific tasks (e.g., touch screen selection) or to allow the crewmember the ability to rest with onset of symptoms. Based on anecdotal reports and performance on computerized dynamic posturography, multiple testing on landing day appeared to be beneficial for some participants, while others may have pushed beyond their motion tolerance limit in an effort to complete more FT objectives. Instead of delaying planetary surface operations to allow for recovery, our results suggest that early mobility may be important. Early active self-administered retraining, individualized based on the level of initial impairment and motion sensitivity, will enable a more efficient motor learning and enhance crew performance.

S J Wood↗
NASA NTRS2023

Concept Design for a 5 MW Partially Superconducting Generator

This paper presents a concept design for the 5 MW generators on NASA’s SUSAN hybrid electric flight concept. The performance targets for this machine are 25 kW/kg and 99% efficiency. The concept design is a partially superconducting machine that builds on NASA’s past work on its High Efficiency Megawatt Motor (HEMM). A partially superconducting machine design tool is used to create a preliminary concept design capable of achieving the target specifications for the SUSAN generator. Higher fidelity design and analysis is applied to the preliminary design. After high fidelity analysis the machine is predicted to achieve 22.3 kW/kg and 99.1% efficiency. Lessons learned from this concept design will be incorporated in the next iteration of the machine.

Thomas Tallerico↗
NASA NTRS2023

Concept Design of a 5 MW Partially Superconducting Generator

This paper presents a concept design for the 5 MW generators on NASA’s SUSAN electric flight demonstrator concept vehicle. The performance targets for this machine are 25 kW/kg and 99% efficiency. The concept design is a partially superconducting machine that builds on NASA’s past work on its High Efficiency Megawatt Motor(HEMM). A partially superconducting machine design tool is used to create a preliminary concept design capable of achieving the target specifications for the SUSAN generator. Higher fidelity design and analysis is applied to the preliminary design. After high fidelity analysis the machine is predicted to achieve 22.3 kW/kg and 99.1% efficiency. Lessons learned from this concept design will be incorporated in the next iteration of the machine.

Thomas Tallerico↗
DOE OSTI2024

Efficient Anomaly Detection Driven By Different Machine Learning Architectures And Models

The rapid growth and ubiquitous adoption of the internet and cyber-physical systems (CPS) have fundamentally transformed modern communication, work, and human-system interactions. While networks now form the backbone of critical digital ecosystems, enabling seamless data transmission across diverse, interconnected systems, this increased connectivity also expands the attack surface, making real-time detection of network intrusions and anomalies a pressing challenge. Detecting unusual activities within network infrastructure requires advanced data traffic analysis to differentiate between legitimate and malicious interactions. Traditional approaches to network anomaly detectionâ??such as rule-based and signature-based systemsâ??often depend on predefined patterns to identify known anomalies, limiting their effectiveness against emerging, stealthy, or previously unseen threats. These conventional methods suffer from high false alarm rates and fail to adapt to the ever-evolving nature of network traffic, particularly in large-scale, decentralized environments where data volume, velocity, and variety are constantly increasing. This dissertation presents artificial intelligence (AI)-driven approaches to anomaly detection that leverage graphics processing unit (GPU)-enabled high-performance computing (HPC) platforms for processing massive network traffic data and monitoring the components of cyber-physical systems (CPS) for potentially hazardous conditions. The research advances several key contributions: (1) Designing efficient machine learning techniques for CPS condition monitoring and anomaly detection; (2) enabling federated learning (FL) frameworks that enable distributed detection while preserving data privacy and system resilience; (3) exploring graph-based methodologies combining graph neural networks (GNN) and graph machine learning (ML) approaches for the Internet of Things (IoT) and automotive network security, and (4) performing distributed edge computing optimizations that integrate FL with scalable technologies for reduced communication overhead. Through extensive experiments, these methodologies demonstrate that complex anomaly detection and condition monitoring tasks can be achieved while balancing computational efficiency and detection accuracy through fine-grained network information processing. The frameworks developed in this research establish a robust foundation for network anomaly detection, providing scalable, adaptive, and privacy-preserving solutions for safeguarding CPS and IoT networks in an increasingly interconnected digital landscape. The practical implications of these research findings are significant, as they can inform the development of next-generation network security systems and contribute to the protection of critical infrastructure against sophisticated cyber attacks.

Marfo, William↗
DOE OSTI2023

Accurate prediction of global-density-dependent range-separation parameters based on machine learning

In this work, we develop an accurate and efficient XGBoost machine learning model for predicting the global-density-dependent range-separation parameter, ωGDD, for long-range corrected functional (LRC)-ωPBE. This ωGDDML model has been built using a wide range of systems (11 466 complexes, ten different elements, and up to 139 heavy atoms) with fingerprints for the local atomic environment and histograms of distances for the long-range atomic correlation for mapping the quantum mechanical range-separation values. The promising performance on the testing set with 7046 complexes shows a mean absolute error of 0.001 117 a0−1 and only five systems (0.07%) with an absolute error larger than 0.01 a0−1, which indicates the good transferability of our ωGDDML model. In addition, the only required input to obtain ωGDDML is the Cartesian coordinates without electronic structure calculations, thereby enabling rapid predictions. LRC-ωPBE(ωGDDML) is used to predict polarizabilities for a series of oligomers, where polarizabilities are sensitive to the asymptotic density decay and are crucial in a variety of applications, including the calculations of dispersion corrections and refractive index, and surpasses the performance of all other popular density functionals except for the non-tuned LRC-ωPBE. Finally, LRC-ωPBE (ωGDDML) combined with (extended) symmetry-adapted perturbation theory is used in calculating noncovalent interactions to further show that the traditional ab initio system-specific tuning procedure can be bypassed. The present study not only provides an accurate and efficient way to determine the range-separation parameter for LRC-ωPBE but also shows the synergistic benefits of fusing the power of physically inspired density functional LRC-ωPBE and the data-driven ωGDDML model.

Chemistry↗
DOE OSTI2021

Machine learning-based real-time monitoring system for smart connected worker to improve energy efficiency

Recent advances in machine learning and computer vision brought to light technologies and algorithms that serve as new opportunities for creating intelligent and efficient manufacturing systems. In this study, the real-time monitoring system of manufacturing workflow for the Smart Connected Worker (SCW) is developed for the small and medium-sized manufacturers (SMMs), which integrates state-of-the-art machine learning techniques with the workplace scenarios of advanced manufacturing systems. Specifically, object detection and text recognition models are investigated and adopted to ameliorate the labor-intensive machine state monitoring process, while artificial neural networks are introduced to enable real-time energy disaggregation for further optimization. The developed system achieved efficient supervision and accurate information analysis in real-time for prolonged working conditions, which could effectively reduce the cost related to human labor, as well as provide an affordable solution for SMMs. The competent experiment results also demonstrated the feasibility and effectiveness of integrating machine learning technologies into the realm of advanced manufacturing systems.

42 ENGINEERING↗
DOE OSTI2021

Design of a Robust Memristive Spiking Neuromorphic System with Unsupervised Learning in Hardware

Spiking neural networks (SNN) offer a power efficient, biologically plausible learning paradigm by encoding information into spikes. The discovery of the memristor has accelerated the progress of spiking neuromorphic systems, as the intrinsic plasticity of the device makes it an ideal candidate to mimic a biological synapse. Despite providing a nanoscale form factor, non-volatility, and low-power operation, memristors suffer from device-level non-idealities, which impact system-level performance. To address these issues, this article presents a memristive crossbar-based neuromorphic system using unsupervised learning with twin-memristor synapses, fully digital pulse width modulated spike-timing-dependent plasticity, and homeostasis neurons. Additionally, the implemented single-layer SNN was applied to a pattern-recognition task of classifying handwritten-digits. The performance of the system was analyzed by varying design parameters such as number of training epochs, neurons, and capacitors. Furthermore, the impact of memristor device non-idealities, such as device-switching mismatch, aging, failure, and process variations, were investigated and the resilience of the proposed system was demonstrated.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Hybrid Quantum–Classical Graph Transformers for Efficient Sentiment Analysis

Quantum Machine Learning (QML) offers a promising paradigm that leverages quantum computing principles to develop efficient and expressive models for learning from complex and structured data. Recent advances in natural language processing (NLP) and artificial intelligence (AI) have demonstrated capabilities in understanding, generating, and reasoning over linguistic and multimodal information. In this work, we present the Quantum Graph Transformer (QGT), a hybrid quantum–classical architecture that extends graph transformer capabilities through quantum self-attention. The QGT models variable-length sentences as token graphs, where both the embedding encoding and the self-attention mechanisms are implemented using parameterized quantum circuits (PQCs), enabling efficient contextual learning with significantly fewer trainable parameters. We train QGT using both fully connected and 𝑘 -nearest-neighbor graph structures and evaluate it on five benchmark sentiment-classification datasets. Experimental results show that QGT consistently achieves higher or comparable accuracy to existing quantum NLP models and outperforms a Classical Graph Transformer (CGT) baseline with identical architecture, achieving 29.4 × fewer parameters while requiring 3–5 × fewer samples to reach comparable performance. These findings highlight the potential of graph-based quantum models as scalable and data-efficient architectures for natural language understanding.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗