Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “training”

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 613 records · Page 34
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Elastic distributed training with fast convergence and efficient resource utilization

Distributed learning is now routinely conducted on cloud as well as dedicated clusters. Training with elastic resources brings new challenges and design choices. Prior studies focus on runtime performance and assume a static algorithmic behavior. In this work, by analyzing the impact of of resource scaling on convergence, we introduce schedules for synchronous stochastic gradient descent that proactively adapt the number of learners to reduce training time and improve convergence. Our approach no longer assumes a constant number of processors throughout training. In our experiment, distributed stochastic gradient descent with dynamic schedules and reduction momentum achieves better convergence and significant speedups over prior static ones. Numerous distributed training jobs running on cloud may benefit from our approach.

Cong, Guojing↗
DOE OSTI2025

Accelerated Over-The-Air Neural Receiver Training Using Self-Contrastive Learning

Self-contrastive learning (SCL), a self-supervised learning method, has been shown to improve image and signal classifier accuracies and reduce the training time for neural communications receivers. In particular, prior work has shown that SCL applied as a pre-training step can improve simulated performance of OFDM in 3GPP TDL channel models by reducing the training time of the downstream classification task (demodulation and demapping). In this work a practical implementation demonstrating SCL pre-training using software defined radios (SDRs) is proposed.

Cooke, Corey [ORNL] (ORCID:0000000234263672)↗
DOE OSTI2023

Effect of CLIQ on Training of HL-LHC Quadrupole Magnets

The high-luminosity LHC upgrade requires stronger than LHC low-beta quadrupole magnets to reach the luminosity goals of the project. The project is well advanced and HL-LHC quadrupole magnets are currently being commissioned in US Labs (MQXFA magnets) and CERN (MQXFB magnets). Those are the first Nb 3 Sn magnets to be used in any large particle accelerator. At development stages, many Nb 3 Sn accelerator sub-scale models showed relatively slow training and MQXFA magnets were projected to have low tens of quenches before reaching operational field. Recently it was shown that dedicated capacitor-based de-vices can affect Nb 3 Sn magnet training, and it was suggested that CLIQ, a capacitor-based device intended for quench protection, can do too. Here, the present paper investigates effects on training likely induced by CLIQ, using the base fact that only half the coils in a quadrupole experience upward current modulation at quench because of capacitor discharge. The study encompasses all MQXFA production magnets trained at BNL to date. No other high-statistics data from identical magnets (series) with CLIQ protection exist so far. Implications and opportunities stemming from data analysis are discussed and conclusions drawn.

43 PARTICLE ACCELERATORS↗
DOE OSTI2018

SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks

Going deeper and wider in neural architectures improves their accuracy, while the limited GPU DRAM places an undesired restriction on the network design domain. Deep Learning (DL) practitioners either need to change to less de- sired network architectures, or nontrivially dissect a network across multiGPUs. These distract DL practitioners from concentrating on their original machine learning tasks. We present SuperNeurons: a dynamic GPU memory scheduling runtime to enable the network training far beyond the GPU DRAM capacity. SuperNeurons features 3 memory optimizations, Liveness Analysis, Unified Tensor Pool, and Cost-Aware Recomputation; together they effectively reduce the network-wide peak memory usage down to the maximal memory usage among layers. We also address the performance issues in these memory-saving techniques. Given the limited GPU DRAM, SuperNeurons not only provisions the necessary memory for the training, but also dynamically allocates the memory for convolution workspaces to achieve the high performance. Evaluations against Caffe, Torch, MXNet and TensorFlow have demonstrated that SuperNeurons trains at least 3.2432 deeper network than current ones with the leading performance. Particularly, SuperNeurons can train ResNet2500 that has 104 basic network layers on a 12GB K40c.

Wang, Linnan↗
DOE OSTI2025

Swap Path Network for Robust Person Search Pre-training

This code corresponds to the WACV25 conference paper, "Swap Path Network for Robust Person Search Pre-training". In that paper, we introduce a new model for the person search task called the Swap Path Net (SPNet). The person search task is a problem in computer vision, where we locate and rank matches to an image of a query person in a set of other images where we want to find them. We also introduce a novel pre-training algorithm specific to the Swap Path Net architecture. The code implements pre-training and fine-tuning of the Swap Path Net (SPNet). This includes ingesting image datasets and updating the weights of the SPNet neural network to train it for the person search task. The repository contains code, configs, and instructions to reproduce all results from the paper.

Jaffe, LucasW [Lawrence Livermore National Laborat↗
DOE OSTI2021

Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training

As an important class of spiking neural networks (SNNs), recurrent spiking neural networks (RSNNs) possess great computational power and have been widely used for processing sequential data like audio and text. However, most RSNNs suffer from two problems. 1. Due to the lack of architectural guidance, random recurrent connectivity is often adopted, which does not guarantee good performance. 2. Training of RSNNs is in general challenging, bottlenecking achievable model accuracy. To address these problems, we propose a new type of RSNNs called Skip-Connected Self-Recurrent SNNs (ScSr-SNNs). Recurrence in ScSr-SNNs is introduced in a stereotyped manner by adding self-recurrent connections to spiking neurons. The SNNs with self-recurrent connections can realize recurrent behaviors similar to those of more complex RSNNs while the error gradients can be more straightforwardly calculated due to the mostly feedforward nature of the network. The network dynamics is enriched by skip connections between nonadjacent layers. Moreover, we propose a new backpropagation (BP) method called backpropagated intrinsic plasticity (BIP) to further boost the performance of ScSr-SNNs by training intrinsic model parameters. Unlike standard intrinsic plasticity rules that adjust the neuron's intrinsic parameters according to neuronal activity, the proposed BIP method optimizes intrinsic parameters based on the backpropagated error gradient of a well-defined global loss function in addition to synaptic weight training. Here, based on challenging speech, neuromorphic speech, and neuromorphic image datasets, the proposed ScSr-SNNs can boost performance by up to 2.85% compared with other types of RSNNs trained by state-of-the-art BP methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Adaptive language model training for molecular design

Abstract The vast size of chemical space necessitates computational approaches to automate and accelerate the design of molecular sequences to guide experimental efforts for drug discovery. Genetic algorithms provide a useful framework to incrementally generate molecules by applying mutations to known chemical structures. Recently, masked language models have been applied to automate the mutation process by leveraging large compound libraries to learn commonly occurring chemical sequences (i.e., using tokenization) and predict rearrangements (i.e., using mask prediction). Here, we consider how language models can be adapted to improve molecule generation for different optimization tasks. We use two different generation strategies for comparison, fixed and adaptive. The fixed strategy uses a pre-trained model to generate mutations; the adaptive strategy trains the language model on each new generation of molecules selected for target properties during optimization. Our results show that the adaptive strategy allows the language model to more closely fit the distribution of molecules in the population. Therefore, for enhanced fitness optimization, we suggest the use of the fixed strategy during an initial phase followed by the use of the adaptive strategy. We demonstrate the impact of adaptive training by searching for molecules that optimize both heuristic metrics, drug-likeness and synthesizability, as well as predicted protein binding affinity from a surrogate model. Our results show that the adaptive strategy provides a significant improvement in fitness optimization compared to the fixed pre-trained model, empowering the application of language models to molecular design tasks.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Comprehensive Physical Activity Assessment During U.S. Army Basic Combat Training

Abstract Alemany, JA, Pierce, JR, Bornstein, DB, Grier, TL, Jones, BH, and Glover, SH. Comprehensive physical activity assessment during U.S. Army Basic Combat Training. J Strength Cond Res 36(12): 3505–3512, 2022—Physical activity (PA) volume, intensity, and qualitative contextual information regarding activity type and loads carried are limited during U.S. Army Basic Combat Training (BCT). The purpose of this study was to characterize daily (05:00–20:00 hours) PA during BCT using a comprehensive approach. During 2 10-week BCT cycles ( n = 40 trainees per cycle), pedometers, accelerometers, and direct observation were used to estimate daily step count, PA volume, and intensity. Physical activity intensity was categorized by metabolic equivalents (METs) such as “sedentary” (1–2 METs), “light” (2–3 METs), “moderate” (3–6 METs), or “vigorous” (≥6 METs). Daily PA data were analyzed longitudinally using linear mixed models, with significance set at p ≤ 0.05. The mean daily step count was 13,459 ± 4,376 steps, and the mean daily accelerometer-assessed PA volume and intensity were as follows: sedentary: 505 ± 98 minutes, light: 190 ± 78 minutes, moderate: 168 ± 51 minutes, and vigorous: 14 ± 14 minutes, with no differences between cycles for all measures ( p > 0.50). Cumulative time on feet (∼50%) and sitting (20–25%) accounted for most daily activity types during both cycles. Trainees, on average, carried between 3 and 9 kg, and ≥9 kg, for 60% and 10% of the monitored day, respectively. Basic Combat Training's physical demands are high, where trainees achieved 1.7 to 2.7 times greater daily ambulation and 6 times the recommended weekly moderate-to-vigorous PA compared with civilian counterparts and performed weight-bearing load carriage for nearly half of the day. Basic Combat Training-associated PA may increase injury risk among trainees unaccustomed to arduous PA and exercise. Implementing national PA policies to improve physical fitness and facilitate acclimatization to BCT's high physical demands could reduce public health burdens and military nonreadiness.

Sport Sciences↗
DOE OSTI2023

Improving the Estimation of the Atmospheric Water Vapor Pressure Using Interpretable Long Short-Term Memory Networks: Dataset, Python code, and trained models

Atmospheric water vapor pressure is an essential meteorological control on land surface and hydrologic processes. It is not as frequently observed as other meteorologic conditions, but often inferred through the August–Roche–Magnus formula by simply assuming dew point and daily minimum temperatures are equivalent or by empirically correlating the two temperatures using an aridity correction. The performance of both methods varies considerably across different regions and during different time periods; obtaining consistently accurate estimates across space and time remains a great challenge. We applied an interpretable Long Short-Term Memory (iLSTM) network conditioned on static, location specific attributes to estimate daily vapor pressure for 83 FLUXNET sites in the United States and Canada. This data package includes all raw data of the 83 FLUXNET sites, input data for model training/validation/test, trained models and results, and python codes for the manuscript "Improving the Estimation of the Atmospheric Water Vapor Pressure Using an Interpretable Long Short-term Memory Network". Specifically, it consists of five parts. - First, "1_Daymet_data_83sites.zip" includes raw data downloaded from Daymet for the 83 sites used in the paper according to their longitude and latitude, in which vapor pressure is used. It also includes a pre-processed CSV data file combining all data from the 83 sites which is specifically used for the paper. - Second, "2_Fluxnet2015_data_83sites.zip" includes raw half hourly data of the 83 sites downloaded from FLUXNET2015 data portal, pre-processed daily data of the 83 sites, a CSV file including combined pre-processed daily data of the 83 sites, and a CSV file including the information (site ID, site name, latitude, longitude, data available period) of the 83 sites. - Third, "3_MODIS_LAI_data_83sites_raw.zip" includes raw leaf area index (LAI) data downloaded from the AppEEARs data portal. - Fourth, "4_Scripts.zip" includes all scripts related to model training and post-processing of a trained model, and a jupyter notebook showing an example for model post-processing. Two typo errors in files titled "run2get_args.py" and "postprocess.py" were corrected on March 27, 2024 to avoid confusions. - Finally, "Trained_models_and_results.zip" includes three folders and three files with suffix ".npy", and each folder corresponds to one file with suffix ".npy" with the same title. Each of the three folders include all trained models associated with one iLSTM model configuration (35 models for each configuration, details are described in the paper). Each file with suffix ".npy" includes the post-processed results of the corresponding 35 models under one iLSTM model configuration.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Reducing Frequency Bias of Fourier Neural Operators in 3D Seismic Wavefield Simulations Through Multistage Training

The recent development of neural operator (NeurOp) learning for solutions to the elastic wave equation shows promising results and provides the basis for fast large-scale simulations for different seismological applications. In this article, we use the Fourier neural operator (FNO) model to directly solve the 3D Helmholtz wave equation for fast seismic ground-motion simulations on different frequencies and show the frequency bias of the FNO model, that is, it learns the lower frequencies better comparing to the higher frequencies. To reduce the frequency bias, we adopt the multistage FNO training, that is, after training a stage 1 FNO model for estimating the ground motion, we use a second FNO model as the stage 2 to learn from the residual, which greatly reduced the errors on the higher frequencies. By adopting this multistage training, the FNO models show reduced biases on higher frequencies, which enhanced the overall results of the ground-motion simulations. Thus the multistage training FNO improves the accuracy and realism of the ground-motion simulations.

earthquakes↗
DOE OSTI2014

Carbon Capture and Storage Training Northwest - CCSTNW (Final Scientific Technical Report) [Slides]

This report details the activities of the Carbon Capture and Storage Training Northwest (CCSTNW) program 2009 to 2013. The CCSTNW created, implemented, and provided Carbon Capture and Storage (CCS) training over the period of the program. With the assistance of an expert advisory board, CCSTNW created curriculum and conducted three short courses, more than three lectures, two symposiums, and a final conference. The program was conducted in five phases; 1) organization, gap analysis, and form advisory board; 2) develop list serves, website, and tech alerts; 3) training needs survey; 4) conduct lectures, courses, symposiums, and a conference; 5) evaluation surveys and course evaluations. This program was conducted jointly by Environmental Outreach and Stewardship Alliance (dba. Northwest Environmental Training Center – NWETC) and Pacific Northwest National Laboratories (PNNL).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2018

Training and Certification Programs on Industrial Energy Systems in the United States

The major industrial energy systems commonly found in manufacturing facilities are compressed air, ammonia refrigeration, chilled water, steam, process heating, combined heat and power, pumps, and fans. The efficiency of these systems contributes significantly to the whole-facility energy performance. On the national and even the international level, well-structured training and highly recognized certification programs help develop a highly skilled and qualified workforce to maintain and improve facilities' energy performance, particularly as technologies within these systems become more and more advanced. The purpose of this paper is to review currently available vendor-agnostic training and certification programs focusing on these systems and to identify the gap between market needs and currently available programs. Its three major conclusions are (1) most training programs focus on operations, maintenance, safety, and design although some briefly touch on energy performance aspects. (2) The Certified Refrigeration Energy Specialist certification by RETA the and Pump System Assessment Professional certification by HI were the only certifications found to be tool-agnostics and emphasize knowledge and skills for improving and maintaining systems energy performance. (3) Developing energy efficiency focused training and ANSI accredited certification programs for industrial energy systems will fill the gap between market needs and currently available programs.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2019

Royal Medical Services Training Centre Assessment

The following document represents the joint SNL/IBCTR and HDR Team's Training Centre needs assessment for the Jordan Royal Medical Service (RMS) at the King Hussein Medical Centre (KHMC) and should be used as follows: 1) To present options for future facility improvements. 2) In support of obtaining additional funding for the facility and finalization of a plan for equipment, human resource development, and technical assistance. 3) as a platform to guide future considerations to provide training centre facilities in support of the Biorisk Management (BRM) training and other training to compliment RMS capabilities.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

RCT Continuing Training 1st Quarter 2022 Presentation Transcript

Welcome to RCT Continuing Training. This training will discuss the process for: collecting and evaluating radiological air samples and submitting samples to HPAL. This training consists of viewing the online presentation and completing its associated exercise guide, Utrain number 53850. It is recommended that you have the exercise guide with you while following along with the online training

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2022

Orientation to NPHR: Scripts for Training

The IAEA is training staff to train member states to use the Nuclear Power Human Resources (NPHR) model, developed at LANL, to examine their human resource plans. Part of the NPHR training involves orienting users to the files used by NPHR, namely the data file and the model files. To assist the IAEA trainers, the scripts in this document were developed for conducting the orientation sections. The scripts are intended to be used as resources for the trainers to develop their ability to deliver the orientation and not as scripts to be read to a training workshop. The scripts are accompanied by video recordings to illustrate what the trainers will show participants during the orientation.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2022

Summary of NDC Capacity Building Workshop and Regional Seismic Travel Time (RSTT) in combination with Data Sharing and Integration Training

The NNSA Seismic Cooperation Program (SCP) sponsored Stephen Myers (LLNL), Michael Begnaud (LANL), Brian Young (SNL) and Istvan Bondar (Research Center for Astronomy and Earth Sciences, Hungary) to serve as a presenters/trainers at the “NDC Capacity Building Workshop and Regional Seismic Travel Time (RSTT) in combination with Data Sharing and Integration Training” September 4-8 2022 in Muscat, Oman (See Appendix A for the agenda). The workshop and training (workshop from here forward) was organized by the Comprehensive Nuclear-Test-Ban Treaty Organization (CTBTO) Provisional Technical Secretariat (PTS). The first half of the week was devoted to NDC workshop activities, and the second half was devoted to RSTT training. Fifty-five participants from 27 countries and the CTBTO-PTS attended the 5-day workshop (See Appendix B for list of participants and countries of origin). Presentations from the PTS described the International Monitoring System (IMS), International Data Centre (IDC) products, and metrics of regional data utilization. Contributed presentations from each country’s scientists included descriptions of regional and national networks, methods of data analysis, and needs for material and technical assistance. Training included an overview of the RSTT method and instruction on how to locate seismic events with the iLoc program, which utilizes RSTT travel times to reduce bias in event location estimates. Methods of seismic tomography and the need for a high-quality tomographic set, including seismological “ground truth”, were emphasized. Seismological “ground truth” or “GT” is a term that has come to mean both events with known location and events with well-characterized locations that are estimated using seismological data, typically with epicenter accuracy of 5 km or better. Notably, the instructional platform has migrated from UNIX shell scripts to Jupyter Notebooks. Jupyter Notebooks have the advantage being more visually intuitive, including display of graphics within the notebook. Each notebook includes every processing step that participants need to reproduce the entire exercise.

58 GEOSCIENCES↗
DOE OSTI2023

Virtual Community Trains

When access to transit solutions is restricted to parts of a community, a division occurs what leads to disadvantaged socioeconomic conditions that only grows over time. This restriction causes difficulties in accessing needed resources such as medical facilities, employment, healthy food, education, healthy food, and more. To solve this restricted access, Labyrinth Smart Mobility and partners are developing a virtual community train that encourages scalability, energy efficiency, and equitability to all regardless of individual circumstances and limitation. The implementation of virtual community trains allows access to resources previously out of reach. The virtual community train enables one operator to drive a lead vehicle. This lead vehicle would then provide direction to a follow vehicle through vehicle-to-vehicle communication. Labyrinth Smart Mobility in conjunction with partners used various methods and resources to prove market feasibility, technical feasibility, economic need and viability, and more as well as design system requirements and architecture emphasis efficiency and safety. In doing so, Labyrinth Smart Mobility and partners will continue these advancements to further develop the virtual community train.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2023

Effect of CLIQ on training of HL-LHC quadrupole magnets

The high-luminosity LHC upgrade requires stronger than LHC low-beta magnets to reach the luminosity goals of the project. The project is well advanced and HL-LHC quadrupole magnets are currently being commissioned in US Labs (MQXFA magnets) and CERN (MQXFB magnets). Those are the first Nb3Sn magnets to be used in any large particle accelerator. At development stages, many Nb3Sn accelerator sub-scale models showed relatively slow training and MQXFA magnets were projected to have low tens of quenches before reaching operational field. Recently it was shown that dedicated capacitor-based devices can affect Nb3Sn magnet training, and it was suggested that CLIQ, a capacitor-based device intended for quench protection, can do too. The present paper investigates effects on training induced by CLIQ, using the base fact that only half the coils in a quadrupole experience upward current modulation because of the capacitor discharge. The study encompasses all MQXFA production magnets trained at BNL to date. No other high-statistics data from identical magnets (series) with CLIQ protection exists so far. Implications and opportunities stemming from data analysis are discussed and conclusions drawn.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗