SEARCH · Search NASA
Results for “TRAINING - UNIVERSITIES”
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.
Flue Gas Desulfurization Wastewater Composition and Implications for Regulatory and Treatment Train Design
The U.S. Environmental Protection Agency is currently revising its regulations on trace element discharges from flue gas desulfurization (FGD) wastewater.<br>In this work, we expand a predictive model of trace element behavior at coal-fired power plants (CFPPs) to estimate the trace element concentration of FGD wastewater at the plant level. We demonstrate that variation in trace element concentrations in FGD wastewater can span several orders of magnitude and is a function of both coal rank and installed air pollution control devices. This conclusion suggests that the benefits and costs of FGD wastewater treatment for the median plant will poorly describe the actual benefits and costs over the full range of existing CFPPs.
2025 Peregrine in-situ monitoring and training dataset for laser powder bed fusion and binder jet printers
Peregrine, a software tool developed at Oak Ridge National Laboratory (ORNL), was used to collect and analyze in-situ monitoring (ISM) data from a Concept Laser M2 (Colibrium Additive) laser powder bed fusion (L-PBF) printer and an ExOne Innovent (Desktop Metal) binder jet printer. Data for four builds (print jobs) were saved to HDF5 (high performance data) files for release. Additionally, process anomalies were annotated by the authors across 37 image stacks (i.e., print layers) and are also provided as HDF5 files.
TSQP Writing Training Implementation Matrices & Training Program Plans [Slides]
This slideshow presentation contains content that accompanies an in person, instructor led course.
TSQP Writing Training Implementation Matrices & Training Program Plans Interactive Notebook
This interactive notebook will guide you through this course. Here you will find the slide information, space for note taking, knowledge checks, and activities. If you have any questions regarding the functioning of this notebook, please don’t hesitate to ask your instructor.
We Train AI, Why Not Humans, Too? An Exploration of Human-AI Team Training for Future Workplace Viability & Integration [SLIDES]
Explore the source record for details and available documents.
We Train AI, Why Not Humans, Too? An Exploration of Human-AI Team Training for Future Workplace Viability
Explore the source record for details and available documents.
Training a Quantum Annealing Based Restricted Boltzmann Machine on Cybersecurity Data
A restricted Boltzmann machine (RBM) is a generative model that could be used in effectively balancing a cybersecurity dataset because the synthetic data a RBM generates follows the probability distribution of the training data. RBM training can be performed using contrastive divergence (CD) and quantum annealing (QA). QA-based RBM training is fundamentally different from CD and requires samples from a quantum computer. We present a real-world application that uses a quantum computer. Specifically, we train a RBM using QA for cybersecurity applications. The D-Wave 2000Q has been used to implement QA. RBMs are trained on the ISCX data, which is a benchmark dataset for cybersecurity. For comparison, RBMs are also trained using CD. CD is a commonly used method for RBM training. Our analysis of the ISCX data shows that the dataset is imbalanced. We present two different schemes to balance the training dataset before feeding it to a classifier. The first scheme is based on the undersampling of benign instances. The imbalanced training dataset is divided into five sub-datasets that are trained separately. A majority voting is then performed to get the result. Our results show the majority vote increases the classification accuracy up from 90.24% to 95.68%, in the case of CD. For the case of QA, the classification accuracy increases from 74.14% to 80.04%. In the second scheme, a RBM is used to generate synthetic data to balance the training dataset. We show that both QA and CD-trained RBM can be used to generate useful synthetic data. Balanced training data is used to evaluate several classifiers. Among the classifiers investigated, K-Nearest Neighbor (KNN) and Neural Network (NN) perform better than other classifiers. They both show an accuracy of 93%. Our results show a proof-of-concept that a QA-based RBM can be trained on a 64-bit binary dataset. The illustrative example suggests the possibility to migrate many practical classification problems to QA-based techniques. Further, we show that synthetic data generated from a RBM can be used to balance the original dataset.
Towards Compact Neural Networks via End-to-End Training: A Bayesian Tensor Approach with Automatic Rank Determination
Post-training model compression can reduce the inference costs of deep neural networks, but uncompressed training still consumes enormous hardware resources and energy. To enable low-energy training on edge devices, it is highly desirable to directly train a compact neural network from scratch with a low memory cost. Low-rank tensor decomposition is an effective approach to reduce the memory and computing costs of large neural networks. However, directly training low-rank tensorized neural networks is a very challenging task because it is hard to determine a proper tensor rank a priori, and the tensor rank controls both model complexity and accuracy. Here, this paper presents a novel end-to-end framework for low-rank tensorized training. We first develop a Bayesian model that supports various low-rank tensor formats (e.g., CANDECOMP/PARAFAC, Tucker, tensor-train, and tensor-train matrix) and reduces neural network parameters with automatic rank determination during training. Then we develop a customized Bayesian solver to train large-scale tensorized neural networks. Our training methods shows orders-of-magnitude parameter reduction and little accuracy loss (or even better accuracy) in the experiments. On a very large deep learning recommendation system with over 4.2 ×10 9 model parameters, our method can reduce the parameter number to 1.6 ×10 5 automatically in the training process (i.e., by 2.6 ×10 4 times) while achieving almost the same accuracy. Code is available at https://github.com/colehawkins/bayesian-tensor-rank-determination.
Physics-Based Method for Generating Fully Synthetic IV Curve Training Datasets for Machine Learning Classification of PV Failures
Classification machine learning models require high-quality labeled datasets for training. Among the most useful datasets for photovoltaic array fault detection and diagnosis are module or string current-voltage (IV) curves. Unfortunately, such datasets are rarely collected due to the cost of high fidelity monitoring, and the data that is available is generally not ideal, often consisting of unbalanced classes, noisy data due to environmental conditions, and few samples. In this paper, we propose an alternate approach that utilizes physics-based simulations of string-level IV curves as a fully synthetic training corpus that is independent of the test dataset. In our example, the training corpus consists of baseline (no fault), partial soiling, and cell crack system modes. The training corpus is used to train a 1D convolutional neural network (CNN) for failure classification. The approach is validated by comparing the model’s ability to classify failures detected on a real, measured IV curve testing corpus obtained from laboratory and field experiments. Results obtained using a fully synthetic training dataset achieve identical accuracy to those obtained with use of a measured training dataset. When evaluating the measured data’s test split, a 100% accuracy was found both when using simulations or measured data as the training corpus. When evaluating all of the measured data, a 96% accuracy was found when using a fully synthetic training dataset. The use of physics-based modeling results as a training corpus for failure detection and classification has many advantages for implementation as each PV system is configured differently, and it would be nearly impossible to train using labeled measured data.
Active Learning A Neural Network Model For Gold Clusters & Bulk From Sparse First Principles Training Data
Small metal clusters are of fundamental scientific interest and of tremendous significance in catalysis. These nanoscale clusters display diverse geometries and structural motifs depending on the cluster size; a knowledge of this size-dependent structural motifs and their dynamical evolution has been of longstanding interest. Given the high computational cost of first-principles calculations, molecular modeling and atomistic simulations such as molecular dynamics (MD) has proven to be an important complementary tool to aid this understanding. Classical MD typically employ predefined functional forms which limits their ability to capture such complex size-dependent structural and dynamical transformation. Neural Network (NN) based potentials represent flexible alternatives and in principle, well-trained NN potentials can provide high level of flexibility, transferability and accuracy on-par with the reference model used for training. A major challenge, however, is that NN models are interpolative and requires large quantities (similar to 10 4 or greater) of training data to ensure that the model adequately samples the energy landscape both near and far-from-equilibrium. A highly desirable goal is minimize the number of training data, especially if the underlying reference model is first-principles based and hence expensive. In this work, we introduce an active learning (AL) scheme that trains a NN model on-the-fly with minimal amount of first-principles based training data. Our AL workflow is initiated with a sparse training dataset (similar to 1 to 5 data points) and is updated on-the-fly via a Nested Ensemble Monte Carlo scheme that iteratively queries the energy landscape in regions of failure and updates the training pool to improve the network performance. Using a representative system of gold clusters, we demonstrate that our AL workflow can train a NN with similar to 500 total reference calculations. Using an extensive DFT test set of similar to 1100 configurations, we show that our AL-NN is able to accurately predict both the DFT energies and the forces for clusters of a myriad of different sizes. Our NN predictions are within 30 meV/atom and 40 meV/angstrom of the reference DFT calculations. Moreover, our AL-NN model also adequately captures the various size-dependent structural and dynamical properties of gold clusters in excellent agreement with DFT calculations and available experiments. We finally show that our AL-NN model also captures bulk properties reasonably well, even though they were not included in the training data.
The impacts of training on change deafness and build-up in a flicker task
Performance on auditory change detection tasks can be improved by training. We examined the stimulus specificity of these training effects in behavior and ERPs. A flicker change detection task was employed in which spatialized auditory scenes were alternated until a "change" or "same" response was made. For half of the trials, scenes were identical. The other half contained changes in the spatial locations of objects from scene to scene. On Day 1, participants were either trained on this auditory change detection task (trained group), or trained on a non-auditory change detection task (control group). On Day 2, all participants were tested on the flicker task while EEG was recorded. The trained group showed greater change detection accuracy than the control group. They were less biased to respond "same" and showed full generalization of learning from trained to novel auditory objects. ERPs for "change" compared to "same" trials showed more negative going P1, N1, and P2 amplitudes, as well as a larger P3b amplitude. The P3b amplitude also differed between the trained and control group, with larger amplitudes for the trained group. Analysis of ERPs to scenes viewed prior to a decision revealed build-up of a difference between "change" and "same" trials in N1 and P2. Results demonstrate that training has an impact early in the "same" versus "change" decision-making process, and that the flicker paradigm combined with the ERP method can be used to study the build-up of change detection in auditory scenes.
How Low Can You Go? Using Synthetic 3D Imagery to Drastically Reduce Real-World Training Data for Object Detection
Deep convolutional neural networks (DCNNs) currently provide state-of-the-art performance on image classification and object detection tasks, and there are many global security mission areas where such models could be extremely useful. Crucially, the success of these models is driven in large part by the widespread availability of high-quality open source data sets such as Image Net, Common Objects in Context (COCO), and KITTI, which contain millions of images with thousands of unique labels. However, global security relevant objects-of-interest can be difficult to obtain: relevant events are low frequency and high consequence; the content of relevant images is sensitive; and adversaries and proliferators seek to obscure their activities. For these cases where exemplar data is hard to come-by, even fine-tuning an existing model with available data can be effectively impossible. Recent work demonstrated that models can be trained using a combination of real-world and synthetic images generated from 3D representations; that such models can exceed the performance of models trained using real-world data alone; and that the generated images need not be perfectly realistic (Tremblay, et al., 2018). However, this approach still required hundreds to thousands of real-world images for training and fine tuning, which for sparse, global security-relevant datasets can be an unrealistic hurdle. In this research, we validate the performance and behavior of DCNN models as we drive the number of real-world images used for training object detection tasks down to a minimal set. We perform multiple experiments to identify the best approach to train DCNNs from an extremely small set of real-world images. In doing so, we: Develop state-of-the-art, parameterized 3D models based on real-world images and sample from their parameters to increase the variance in synthetic image training data; Use machine learning explainability techniques to highlight and correct through targeted training the biases that result from training using completely synthetic images; and Validate our results by comparing the performance of the models trained on synthetic data to one another, and to a control model created by fine-tuning an existing ImageNet-trained model with a limited number (hundreds) of real-world images.
The effects of 8-week complex training on lower-limb strength and power of Chinese elite female modern pentathlon athletes
Complex training (CT) is a combination training method that alternates between performing high-load resistance training (RT) and plyometric training within one single session. The study aimed to examine the effects of CT on lower-limb strength and power of elite female modern pentathlon athletes under the new modern pentathlon format and competition rules. Ten female participants (age: 23.55 ± 2.22 years, weight: 60.59 ± 3.87 kg, height: 169.44 ± 4.57 cm, and training experience: 6.90 ± 2.08 years) of the national modern pentathlon team completed 8 weeks of RT as followed by 8 weeks of CT, with 2 weeks of break. Then, the participants conducted 8 weeks of CT, which included RT combined with plyometric training (e.g., drop jump and continuous jump). All stages of training were designed by the linear strength training period theories, requiring participants to train twice for the first 4 weeks and three times for the second 4 weeks. The one-repetition maximum (1RM) of squat, isometric mid-thigh pull (IMTP), counter-movement jump (CMJ), squat jump (SJ), pre-stretch augmentation percentage (PSAP), and reaction strength index (RSI) were assessed before and after both RT and CT training. One-way repeated-measure ANOVA models revealed that the 1RM of squat was significantly improved ( p < 0.001) after RT as compared to pre-RT. No significant improvement in IMTP ( p = 0.055), CMJ ( p = 0.194), SJ ( p = 0.692), PSAP ( p = 0.087), and RSI ( p = 0.238) was not observed. After CT, 1RM of squat ( p < 0.001), IMTP ( p < 0.035), CMJ ( p < 0.001), SJ ( p < 0.008), RSI ( p < 0.006) were significant improved as compared to pre-RT, post-RT and pre-CT, while significant improvements in PSAP were observed as compared to pre-RT ( p = 0.003) and pre-CT ( p = 0.027), but not to post-RT ( p = 0.156). This pilot study showed the promise of CT following RT to improve lower-limb strength and power in elite female modern pentathlon athletes. The findings are worthwhile to be confirmed in future studies with larger sample size and randomized design.
Improving Photometric Redshift Estimates with Training Sample Augmentation
Abstract Large imaging surveys will rely on photometric redshifts (photo- z 's), which are typically estimated through machine-learning methods. Currently planned spectroscopic surveys will not be deep enough to produce a representative training sample for Legacy Survey of Space and Time (LSST), so we seek methods to improve the photo- z estimates that arise from nonrepresentative training samples. Spectroscopic training samples for photo- z 's are biased toward redder, brighter galaxies, which also tend to be at lower redshift than the typical galaxy observed by LSST, leading to poor photo- z estimates with outlier fractions nearly 4 times larger than for a representative training sample. In this Letter, we apply the concept of training sample augmentation, where we augment simulated nonrepresentative training samples with simulated galaxies possessing otherwise unrepresented features. When we select simulated galaxies with ( g - z ) color, i -band magnitude, and redshift outside the range of the original training sample, we are able to reduce the outlier fraction of the photo- z estimates for simulated LSST data by nearly 50% and the normalized median absolute deviation (NMAD) by 56%. When compared to a fully representative training sample, augmentation can recover nearly 70% of the degradation in the outlier fraction and 80% of the degradation in NMAD. Training sample augmentation is a simple and effective way to improve training samples for photo- z 's without requiring additional spectroscopic samples.
FLEET: Flexible Efficient Ensemble Training for Heterogeneous Deep Neural Networks
Parallel training of an ensemble of Deep Neural Networks (DNN) on a cluster of nodes is an effective approach to shorten the process of neural network architecture search and hyper-parameter tuning for a given learning task. Prior efforts have shown that data sharing, where the common preprocessing operation is shared across the DNN training pipelines, saves computational resources and improves pipeline efficiency. Data sharing strategy, however, performs poorly for a heterogeneous set of DNNs where each DNN has varying computational needs and thus different training rate and convergence speed. This paper proposes FLEET, a flexible ensemble DNN training framework for efficiently training a heterogeneous set of DNNs. We build FLEET via several technical innovations. We theoretically prove that an optimal resource allocation is NP-hard and propose a greedy algorithm to efficiently allocate resources for training each DNN with data sharing. We integrate data-parallel DNN training into ensemble training to mitigate the differences in training rates and introduce checkpointing into this context to address the issue of different convergence speeds. Experiments show that FLEET significantly improves the training efficiency of DNN ensembles without compromising the quality of the result.
Current Status of the DOE/NNSA Nuclear Criticality Safety Program Hands-On Criticality Safety Training
The U.S. Department of Energy/National Nuclear Security Administration (DOE/NNSA) Nuclear Criticality Safety Program (NCSP) has conducted two-week Nuclear Criticality Safety (NCS) Practitioner courses since 2011 to support the training and qualification of new NCS staff. The course was developed in accordance with the American National Standard Institute/American Nuclear Society (ANSI/ANS) standard for NCS training and qualifications (ANSI/ANS-8.26-2007). In 2013, an NCS Manager’s course was developed for process supervisors, managers, regulators, and other professionals with NCS-related responsibilities. This course was revised in 2019 for Criticality Safety Officers (CSOs) based on an NCSP Criticality Safety Support Group tasking (2018-01). This course was piloted at the Nevada Field Office and the National Criticality Experiments Research Center (NCERC) in June 2021. These courses consist of the following training components: classroom education, facility training, and hands-on subcritical and critical experiments training. The two-week Practitioner course offers a week of classroom training, with practical workshops and exercises focused on teaching students how to perform an NCS evaluation. The second week of training involves hands-on critical and subcritical experiments and measurements. The first week is offered in Las Vegas, Nevada, at the DOE Nevada Field Office or the National Atomic Testing Museum. Depending on the student’s clearance level, the second week is offered at Sandia National Laboratory (SNL) (uncleared and L-cleared students) or at the National Criticality Experiments Research Center (Q-cleared students). The one-week Manager’s course is offered at SNL or NCERC, depending on clearance or interest, and includes classroom and hands- on critical and subcritical experiments and measurements. This paper provides an overview and status report for the DOE/NNSA NCSP training courses in NCS and to provide information about future course offerings. This paper discusses the challenges associated with executing the training courses during the COVID-19 pandemic. The 2-week Practitioner and 1-week manager courses are currently offered twice per year and adjustments are made based upon demand.
Current Status of the DOE/NNSA Nuclear Criticality Safety Program Hands-On Criticality Safety Training [Abstract]
The U.S. Department of Energy/National Nuclear Security Administration (DOE/NNSA) Nuclear Criticality Safety Program (NCSP) has conducted two-week Nuclear Criticality Safety (NCS) Practitioner courses since 2011 to support the training and qualification of new NCS staff. The course was developed in accordance with the American National Standard Institute/American Nuclear Society (ANSI/ANS) standard for NCS training and qualifications (ANSI/ANS-8.26-2007). In 2013, an NCS Manager’s course was developed for process supervisors, managers, regulators, and other professionals with NCS-related responsibilities. This course was revised in 2019 for Criticality Safety Officers (CSOs) based on an NCSP Criticality Safety Support Group tasking (2018-01). This course was piloted at the Nevada Field Office and the National Criticality Experiments Research Center (NCERC) in June 2021. These courses consist of the following training components: classroom education, facility training, and hands-on subcritical and critical experiments training. The two-week Practitioner course offers a week of classroom training, with practical workshops and exercises focused on teaching students how to perform an NCS evaluation. The second week of training involves hands-on critical and subcritical experiments and measurements. The first week is offered in Las Vegas, Nevada, at the DOE Nevada Field Office or the National Atomic Testing Museum. Depending on the student’s clearance level, the second week is offered at Sandia National Laboratory (SNL) (uncleared and L-cleared students) or at the National Criticality Experiments Research Center (Q-cleared students). The one-week Manager’s course is offered at SNL or NCERC, depending on clearance or interest, and includes classroom and hands-on critical and subcritical experiments and measurements. This paper provides an overview and status report for the DOE/NNSA NCSP training courses in NCS and to provide information about future course offerings. This paper will also discuss the challenges associated with executing the training courses during the COVID-19 pandemic. The 2-week Practitioner and 1-week manager courses are currently offered twice per year and adjustments are made based upon demand.