Search NASA⌕ Search

SEARCH · Search NASA

Results for “training effectiveness”

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

Impact of Domain Knowledge on the Property Prediction of Specialized Machine Learning Models

Developing transferable machine learning models is trending in data-driven materials research. However, how to apply such models to a specific research domain remains unclear. Here, in this work, we choose high-entropy materials as a platform with a specialized data set containing 145,323 DFT-relaxed materials. This data set is used to explore the role of domain-specific knowledge in training effective models. Our tests with three representative graph neural network architectures indicate the model complexity has much smaller influence on performance than the data itself. Specifically, the consideration of low-energy atomic ordering, structures with diverse elemental coverage, and high-order interactions significantly influences the model performance. We also find that domain knowledge-driven sampling can greatly enhance unsupervised learning techniques. This research highlights that developing specialized data sets is more beneficial than further complicating deep learning architectures. Additionally, physics-inspired sampling algorithms are crucially needed for better machine learning models for a specific materials research domain.

36 MATERIALS SCIENCE↗

Nonlinear encoding in diffractive information processing using linear optical materials

Nonlinear encoding of optical information can be achieved using various forms of data representation. Here, we analyze the performances of different nonlinear information encoding strategies that can be employed in diffractive optical processors based on linear materials and shed light on their utility and performance gaps compared to the state-of-the-art digital deep neural networks. For a comprehensive evaluation, we used different datasets to compare the statistical inference performance of simpler-to-implement nonlinear encoding strategies that involve, e.g., phase encoding, against data repetition-based nonlinear encoding strategies. We show that data repetition within a diffractive volume (e.g., through an optical cavity or cascaded introduction of the input data) causes the loss of the universal linear transformation capability of a diffractive optical processor. Therefore, data repetition-based diffractive blocks cannot provide optical analogs to fully connected or convolutional layers commonly employed in digital neural networks. However, they can still be effectively trained for specific inference tasks and achieve enhanced accuracy, benefiting from the nonlinear encoding of the input information. Our results also reveal that phase encoding of input information without data repetition provides a simpler nonlinear encoding strategy with comparable statistical inference accuracy to data repetition-based diffractive processors. Our analyses and conclusions would be of broad interest to explore the push-pull relationship between linear material-based diffractive optical systems and nonlinear encoding strategies in visual information processors.

42 ENGINEERING↗

Exchange bias in NiFe/granular-FeMn-MgO bilayers

A series of polycrystalline NiFe/(FeMn){sub 1-x}(MgO){sub x} bilayers with granular antiferromagnetic layers were prepared by magnetron sputtering. For a specific antiferromagnetic layer thickness, the intensity of the fcc (111) x-ray diffraction peaks from Cu, NiFe, and FeMn layers, and the FeMn grain size exhibit maxima at x=0.025. At this composition, significant enhancement in exchange field is observed together with slight change in coercivity. Remarkably, the training effect in exchange bias is greatly suppressed. These observations indicate the possibility of utilizing granular antiferromagnetic layers in magnetoelectronic devices to improve thermal stability.

36 MATERIALS SCIENCE↗

Detection of bottom ferromagnetic electrode oxidation in magnetic tunnel junctions by magnetometry measurements

Surface oxidation of the bottom ferromagnetic (FM) electrode, one of the major detrimental factors to the performance of a magnetic tunnel junction (MTJ), is difficult to avoid during the fabrication process of the MTJ's tunnel barrier. Since Co rich alloys are commonly used for the FM electrodes in MTJs, overoxidation of the tunnel barrier results in the formation of a CoO antiferromagnetic (AF) interface layer which couples with the bottom FM electrode to form a typical AF/FM exchange bias (EB) system. In this work, surface oxidation of the CoFe and CoFeB bottom electrodes was detected via magnetometry measurements of EB characterizations including the EB field, training effect, uncompensated spin density, and enhanced coercivity. Variations in these parameters were found to be related to the surface oxidation of the bottom electrode, among them the change in coercivity is most sensitive. Annealed samples show evidence for an oxygen migration back to the MgO tunnel barrier by annealing.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Thermally driven asymmetric responses of grains versus spin-glass related distributions of blocking temperature in exchange biased Co/IrMn bilayers

Controlling ferromagnetic/antiferromagnetic blocking temperatures in exchange biased based devices appears crucial for applications. The blocking temperature is ascribed to the ability of both antiferromagnetic grains and interfacial spin-glass-like phases to withstand ferromagnetic magnetization reversal. To better understand the respective contributions of grains versus spin-glass, blocking temperature distributions were measured after various thermal treatments for cobalt/iridium-manganese bilayers. The high-temperature contribution linked to antiferromagnetic grains shifts towards lower temperatures above a threshold thermal annealing. In contrast, the occurrence and evolution of training effects for the low-temperature contribution only agree with its inferred interfacial spin-glass-like origin.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Magnetostrictive Fe{sub 73}Ga{sub 27} nanocontacts for low-field conductance switching

The electrical conductance G of magnetostrictive nanocontacts made from Galfenol (Fe{sub 73}Ga{sub 27}) can be reproducibly switched between “on” and “off” states in a low magnetic field of ∼20–30 mT at 10 K. The switching behavior is in agreement with the magnetic field dependence of the magnetostriction inferred from the magnetization behavior, causing a positive magnetostrictive strain along the magnetic field. The repeated magnetic-field cycling leads to a stable contact geometry and to a robust contact configuration with a very low hysteresis of ∼1 mT between opening and closing the contact due to a training effect. Non-integral multiples of the conductance quantum G{sub 0} observed for G > G{sub 0} are attributed to electron backscattering at defect sites in the electrodes near the contact interface. When the contact is closed either mechanically or by magnetic field, the conductance shows an exponential behavior below G{sub 0} due to electron tunneling. This allows to estimate the magnetostriction λ = 4 × 10{sup −5} at 10 K. The results demonstrate that such magnetostrictive devices are suitable for the remote control of the conductance by low magnetic fields in future nanotechnology applications.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DLIO: A DATA-CENTRIC BENCHMARK FOR DEEP LEARNING APPLICATIONS

SF-22-136 Deep learning has been shown as a successful method for various tasks, and its popularity results in numerous open-source deep learning software tools. Deep learning has been applied to a broad spectrum of scientific domains such as cosmology, particle physics, computer vision, fusion, and astrophysics. Scientists have performed a great deal of work to optimize the computational performance of deep learning frameworks. However, the same cannot be said for I/O performance. As deep learning algorithms rely on big-data volume and variety to effectively train neural networks accurately, I/O is a significant bottleneck on large-scale distributed deep learning training. DLIO, is a novel representative benchmark suite built based on the I/O profiling of the selected workloads. DLIO can be utilized to accurately emulate the I/O behavior of modern deep learning applications. Using DLIO, application developers and system software solution architects can identify potential I/O bottlenecks in their applications and guide optimizations to boost the I/O performance leading to lower training times. The storage vendor can also use DLIO as a guide for designing and optimize the storage and filesystem targeting at deep learning application.

ZHENG, HUIHUO↗

Theranostic Radiopnictogens: 71 As, 72 As, and 119 Sb (Final Technical Report)

This project has developed new methods for the cyclotron production of medically relevant radionuclides 71 As and 119 Sb. Arsenic and antimony are chemically homologous elements (group 5A, also known as the pnictogens) that have radionuclides that are of considerable interest within nuclear medicine. Such radiopnictogens include the potentially therapeutic radionuclides 119 Sb (t 1/2 = 38 h) that decays with the emission of 24.5 low energy, high potency electrons per decay with little concomitant photon radiation and 77 As (t 1/2 = 39 h) that decays with average beta energy of 230 keV and diagnostic nuclides 71 As (t 1/2 = 65 h, 28% β+) and 72 As (t 1/2 = 26 h, 80% β+) for positron emission tomography (PET). This work has had major success developing new methods for the cyclotron production and radiochemical isolation of 71 As, supporting parallel developments for 119 Sb, and assessing the chemical similarities between these two homologous radionuclides. This project brought into collaboration two universities with complimentary skill sets, proficiencies, expertise, and facilities: the University of Wisconsin (UWisc) and the University of Missouri (Mizzou). Professors Ellison and Engle have experience in the small cyclotron production and radiochemical isolation of radionuclides, including 72 As and 119 Sb. Their recently developed metallurgic methods for fabricating cyclotron targets have great potential to expand and allow for the biomedical cyclotron production of long- lived, lower positron energy 71 As. Professors Hennkens and Jurisson have significant experience in the reactor production, radiochemical isolation, and biological functionalization of radioarsenic. Recent development of trithiol-based chelator molecules for functionalizing radioarsenic provide a platform for the investigation of the fundamental challenges of the promising low-energy-electron emitter, 119 Sb. Through their positions within their respective University’s graduate schools, the PIs and Co-Is effectively trained of graduate students and postdoctoral researchers in nuclear and radiochemistry, sub-specialties specifically identified in the Department of Energy (DOE) Office of Science Isotope Program long-range plan. Annual laboratory research visits for students between UWisc and Mizzou provided essential broad-field experience and scientific networking that is critical for maintaining their path along the training pipeline to productive careers in isotope production. This research collaboration has provided significant benefits to the DOE University Isotope Network and radionuclide-using researchers around the country.

07 ISOTOPE AND RADIATION SOURCES↗

Construction of Women’s All-Around Speed Skating Event Performance Prediction Model and Competition Strategy Analysis Based on Machine Learning Algorithms

Introduction Accurately predicting the competitive performance of elite athletes is an essential prerequisite for formulating competitive strategies. Women’s all-around speed skating event consists of four individual subevents, and the competition system is complex and challenging to make accurate predictions on their performance. Objective The present study aims to explore the feasibility and effectiveness of machine learning algorithms for predicting the performance of women’s all-around speed skating event and provide effective training and competition strategies. Methods The data, consisting of 16 seasons of world-class women’s all-around speed skating competition results, used in the present study came from the International Skating Union (ISU). According to the competition rules, distinct features are filtered using lasso regression, and a 5,000 m race model and a medal model are built using a fivefold cross-validation method. Results The results showed that the support vector machine model was the most stable among the 5,000 m race and the medal models, with the highest AUC (0.86, 0.81, respectively). Furthermore, 3,000 m points are the main characteristic factors that decide whether an athlete can qualify for the final. The 11th lap of the 5,000 m, the second lap of the 500 m, and the fourth lap of the 1,500 m are the main characteristic factors that affect the athlete’s ability to win medals. Conclusion Compared with logistic regression, random forest, K-nearest neighbor, naive Bayes, neural network, support vector machine is a more viable algorithm to establish the performance prediction model of women’s all-around speed skating event; excellent performance in the 3,000 m event can facilitate athletes to advance to the final, and athletes with outstanding performance in the 500 m event are more likely competitive for medals.

Liu, Meng↗

Decentralized Distributed Proximal Policy Optimization (DD-PPO) for High Performance Computing Scheduling on Multi-User Systems

Resource allocation in High Performance Computing (HPC) environments presents a complex and multifaceted challenge for job scheduling algorithms. Beyond the efficient allocation of system resources, schedulers must account for and optimize multiple performance metrics, including job wait time and system throughput. Traditional heuristic-based scheduling algorithms increasingly struggle and lack the efficiency needed to meet the demands and address the complexity and scale of modern HPC systems. Consequently, recent research efforts have focused on leveraging advancements in Artificial Intelligence (AI) and Deep Learning (DL), particularly Reinforcement Learning (RL), to develop more adaptable and intelligent scheduling strategies. Previous RL-based scheduling approaches have explored a range of algorithms, from Deep Q-Networks (DQN) to Proximal Policy Optimization (PPO), and more recently, hybrid methods that integrate Graph Neural Networks (GNNs) with RL techniques. However, a common limitation across these methods is their reliance on relatively small datasets, with few methods being evaluated using large-scale, multi-million-job trace datasets representative of real-world HPC workloads. Moreover, existing RL schedulers face scalability issues due to centralized policy updates, which hinder training efficiency and performance when applied to large datasets. This study introduces a novel RL-based scheduler utilizing Decentralized Distributed Proximal Policy Optimization (DD-PPO) algorithm, which supports large-scale distributed training across multiple workers without requiring parameter synchronization at every step. By eliminating reliance on centralized updates to a shared policy, the DD-PPO scheduler enhances scalability, training efficiency, and sample utilization. Experimental validation using a large real-world dataset containing over 11.5 million job traces collected from petascale HPC systems over six years assesses the influence of dataset scale on training effectiveness and compares DD-PPO performance to traditional and advanced scheduling approaches. The experimental results demonstrate improved scheduling performance in comparison to both heuristic-based schedulers and existing RL-based scheduling algorithms.

AI↗

Muscle training and blood flow

Isotonic training effects on circulation for limb muscular strength characteristics, using peak blood flow and venous compliance measurements

Carlson, L. D.↗

Conference on General Aviation-Business Flying, University of Tennessee, Tullahoma, Tenn., August 17-19, 1972, Proceedings.

The papers deal with safety measures, commuter airlines, charter and lease flying, pleasure flying and private travel, technology for the next decade, avionics, and the airport network. Attention is given to transfer between general and commercial terminals, airport standards, traffic control, increasing training effectiveness through simulation, proposed revision of Part 61 of FAA regulations, and accident prevention. Individual items are announced in this issue.

Source record↗

A quasi-Newton procedure for identifying pilot-related parameters of the optimal control model

The development and application of a quasi-Newton gradient search procedure for identifying independent pilot related parameters of the optimal control model for pilot/vehicle systems is reported. A sensitivity analysis procedure which determines whether a given model parameter is required to match a specific experimental result, and which experimentally induced parameter changes are required to account for behavioral and performance differences, is described. Application of the identification scheme to training effects in a manual control task is described.

Levison, W. H.↗

Simulation for human factors research. A central question: Fidelity

Generalized outlines are presented for simulation in human factors research. Recent trends in aeronautical simulation are given. Some criteria for effective training devices are also given. Full system/full mission simulation in aviation and in space human factors research is presented.

Nagel, D.↗

Theory underlying CRM training: Psychological issues in flight crew performance and crew coordination

What psychological theory and research can reveal about training in Cockpit Resource Management (CRM) is summarized. A framework is provided for the critical analysis of current approaches to CRM training. Background factors and definitions critical to evaluating CRM are reviewed, followed by a discussion of issues directly related to CRM training effectiveness. Some of the things not known about the optimization of crew performance and the research needed to make these efforts as effective as possible are described.

Helmreich, Robert L.↗