Search NASA⌕ Search

SEARCH · Search NASA

Results for “neural nets”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

BSTC: A Novel Binarized-Soft-Tensor-Core Design for Accelerating Bit-Based Approximated Neural Nets

Binarized neural network (or BNN) promises tremendous performance improvement over traditional DNNs through simplified bit-level computation and significantly reduced memory access/storage cost. In addition, it has other advantages of low-cost, low-energy and high-robustness, showing great utilization potential in resources-constrained, volatile and latency-critical applications, which are critical for future HPC execution. However, the promised significant performance gain of BNN inference has never been fully demonstrated on general-purpose processors, particularly on GPUs, due to: (i) the challenge to extract and leverage sufficient fine-grained bit-level-parallelism to saturate GPU cores when batch is small; (ii) the fundamental design conflict between bit-based BNN algorithm and underlying word-based architecture; (iii) architecture \& performance unfriendly BNN network design. To address (i) and (ii), we propose binarized-soft-tensor-core as a software-hardware codesign approach to construct bit-manipulation capability for modern GPUs to effectively harvest the emerging bit-level-parallelism. To tackle (iii), we propose intra- and inter-layer fusion techniques so that the entire BNN inference can be packed into a single GPU kernel, to avoid high-cost frequent launching. Experiments demonstrate that our design can achieve over 1000x speedup for raw inference latency and 10x for inference throughput over the state-of-the-art full-precision simulated BNN inference for AlexNet on ImageNet.

Li, Ang↗
DOE OSTI2025

Dynamic Model Development of a Wind Power Plant Using Neural Net Method to Forecast Wind Power Output (CRADA Final Report)

This project is intended to model wind power plant based on monitored data at the wind power plant. This project will promote the university research in Renewable Energy area and trains the future highly qualified engineers. The dynamic model will be based on neural net model with the input from the two met towers (12 inputs), and the number of turbines in operation (one input). The overall input will be 13 inputs to drive the simulations. The output power at the point of interconnection will be used to tune the neural net weight coefficients. Two neural net concepts will be investigated (the back propagation neural net and the dynamic recurrent neural net with feedback).

17 WIND ENERGY↗
DOE OSTI2023

Non-parametric Lagrangian biasing from the insights of neural nets

We present a Lagrangian model of galaxy clustering bias in which we train a neural net using the local properties of the smoothed initial density field to predict the late-time mass-weighted halo field.By fitting the mass-weighted halo field in the AbacusSummit simulations at z = 0.5, we find that including three coarsely spaced smoothing scales gives the best recovery of the halo power spectrum. Adding more smoothing scales may lead to 2–5% underestimation of the large-scale power and can cause the neural net to overfit.We find that the fitted halo-to-mass ratio can be well described by two directions in the original high-dimension feature space.Projecting the original features into these two principal components and re-training the neural net either reproduces the original training result, or outperforms it with a better match of the halo power spectrum. The elements of the principal components are unlikely to be assigned physical meanings, partly owing to the features being highly correlated between different smoothing scales.Our work illustrates a potential need to include multiple smoothing scales when studying galaxy bias, and this can be done easily with machine-learning methods that can take in high dimensional input feature space.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2014

The EB factory project. I. A fast, neural-net-based, general purpose light curve classifier optimized for eclipsing binaries

We describe a new neural-net-based light curve classifier and provide it with documentation as a ready-to-use tool for the community. While optimized for identification and classification of eclipsing binary stars, the classifier is general purpose, and has been developed for speed in the context of upcoming massive surveys such as the Large Synoptic Survey Telescope. A challenge for classifiers in the context of neural-net training and massive data sets is to minimize the number of parameters required to describe each light curve. We show that a simple and fast geometric representation that encodes the overall light curve shape, together with a chi-square parameter to capture higher-order morphology information results in efficient yet robust light curve classification, especially for eclipsing binaries. Testing the classifier on the ASAS light curve database, we achieve a retrieval rate of 98% and a false-positive rate of 2% for eclipsing binaries. We achieve similarly high retrieval rates for most other periodic variable-star classes, including RR Lyrae, Mira, and delta Scuti. However, the classifier currently has difficulty discriminating between different sub-classes of eclipsing binaries, and suffers a relatively low (∼60%) retrieval rate for multi-mode delta Cepheid stars. We find that it is imperative to train the classifier's neural network with exemplars that include the full range of light curve quality to which the classifier will be expected to perform; the classifier performs well on noisy light curves only when trained with noisy exemplars. The classifier source code, ancillary programs, a trained neural net, and a guide for use, are provided.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2014

SU-F-BRD-11: Prediction of Dosimetric Endpoints From Patient Geometry Using Neural Nets

Purpose: The previously-published overlap volume histogram (OVH) technique lends itself naturally to prediction of the dose received by a given volume of tissue (e.g. D90) in intensity-modulated radiotherapy (IMRT) treatment plans. Here we extend the OVH technique using artificial neural networks in order to predict the volume of tissue receiving a given dose (e.g. V90) in both prostate IMRT and conventional breast radiotherapy. Methods: Twenty-nine prostate treatment plans and forty-three breast treatment plans were analyzed. The spatial relationships between the prostate and rectum and between the breast and ipsilateral lung were characterized using OVHs. The OVH is a cumulative histogram representing the fractional volume of the risk organ overlapped by a series of isotropic expansions of the planning target volume (PTV). Seven cases were identified as outliers and replanned. OVH points were used as inputs to a one hidden layer feed forward artificial neural network with quality parameters of the corresponding plan, such as the rectum V50, as targets. A 3-fold cross-validation was used to estimate the prediction error. Results: The root mean square (RMS) error between the predicted rectum V50s and the planned values was 2.3, which was 35% of the standard deviation of V50 for the twenty-nine plans. The RMS error of prediction of V20 of the ipsilateral lung in breast cases was 3.9, which was 90% of the standard deviation of the V20 values in the breast plan database. Conclusion: This study demonstrates that artificial neural nets can be used to extend the OVH technique to predict dosimetric endpoints taking the form of a volume receiving a given dose, rather than the minimum dose received by a given volume. Prediction of ipsilateral lung dose in breast radiotherapy using the OVH technique remains a work in progress.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Neural net detection of seismic features related to gas hydrates and free gas accumulations on the northern U.S. Atlantic margin

Bottom-simulating reflections (BSRs) that sometimes mark the base of the gas hydrate stability zone in marine sediments are often identified based on the reverse polarity reflections that cut across stratigraphic layering in seismic amplitude data. On the northern U.S. Atlantic margin (USAM) between Cape Hatteras and Hudson Canyon, legacy seismic data have revealed pronounced BSRs south of the deepwater extension of Hudson Canyon and more subtle ones from offshore Delaware south to Cape Hatteras, where the reflections sometimes follow stratigraphic layering. Using high-resolution seismic data acquired during the 2018 Mid-Atlantic Resource Imaging Experiment and a supervised neural net, we identify seismic features associated with gas hydrates and/or the top of gas between Hudson Canyon and Cape Hatteras. Using seismic attributes especially sensitive to the presence of gas, we train a neural network algorithm on seismic data from an area with strong BSRs and then apply the model to the rest of the data set. The results indicate that gas hydrate and/or shallow free gas are significantly more widespread on the northern part of the USAM than previously known. Seismic indicators of gas extend landward from the 2000 m isobath to the upper continental slope in sectors with (offshore Virginia) and, to a lesser extent, without (offshore New Jersey) pervasive upper slope methane seeps. Higher sand content and intermediate sediment thickness, factors related to the container size and gas charge in a petroleum systems framework, are associated with more robust gas indicators.

Geochemistry & Geophysics↗
DOE OSTI2024

UNNT: A novel Utility for comparing Neural Net and Tree-based models

The use of deep learning (DL) is steadily gaining traction in scientific challenges such as cancer research. Advances in enhanced data generation, machine learning algorithms, and compute infrastructure have led to an acceleration in the use of deep learning in various domains of cancer research such as drug response problems. In our study, we explored tree-based models to improve the accuracy of a single drug response model and demonstrate that tree-based models such as XGBoost (eXtreme Gradient Boosting) have advantages over deep learning models, such as a convolutional neural network (CNN), for single drug response problems. However, comparing models is not a trivial task. To make training and comparing CNNs and XGBoost more accessible to users, we developed an open-source library called UNNT (A novel Utility for comparing Neural Net and Tree-based models). The case studies, in this manuscript, focus on cancer drug response datasets however the application can be used on datasets from other domains, such as chemistry.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Neural net modeling of equilibria in NSTX-U

Neural networks (NNs) offer a path towards synthesizing and interpreting data on faster timescales than traditional physics-informed computational models. In this work we develop two NNs relevant to equilibrium and shape control modeling, which are part of a suite of tools being developed for the National Spherical Torus Experiment-Upgrade for fast prediction, optimization, and visualization of plasma scenarios. The networks include Eqnet, a free-boundary equilibrium solver trained on the EFIT01 (Equilibrium FITtting 01) reconstruction algorithm, and Pertnet, which is trained on the Gspert code and predicts the non-rigid plasma response, a nonlinear term that arises in shape control modeling. The NNs are trained with different combinations of inputs and outputs in order to offer flexibility in use cases. In particular, Eqnet can use magnetic diagnostics as inputs and act as an EFIT-like reconstruction algorithm, or, by using pressure and current profile information the NN can act as a forward Grad–Shafranov equilibrium solver. This forward-mode version is envisioned to be implemented in the suite of tools for simulation of plasma scenarios. The reconstruction-mode version gives some performance improvements compared to the online reconstruction code real-time EFIT, especially when vessel eddy currents are significant. Here, we report strong performance for all NNs indicating that the models could reliably be used within closed-loop simulations or other applications. Some limitations are discussed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

QC-GN 2 oMS 2 : a Graph Neural Net for High Resolution Mass Spectra Prediction

Predicting the mass spectrum of a molecular ion is often accomplished via three generalized approaches: rules-based methods for bond breaking, deep learning, or quantum chemical (QC) modeling. Rules-based approaches are often limited by the conditions for different chemical subspaces and perform poorly under chemical regimes with few defined rules. QC modeling is theoretically robust but requires significant amounts of computational time to produce a spectrum for a given target. Among deep learning techniques, graph neural networks (GNNs) have performed better than previous work with fingerprint-based neural networks in mass spectra prediction. To explore this technique further, we investigate the effects of including quantum chemically derived information as edge features in the GNN to increase predictive accuracy. The models we investigated include categorical bond order, bond force constants derived from extended tight-binding (xTB) quantum chemistry, and acyclic bond dissociation energies. Throughout this work, we evaluated these models against a control GNN with no edge features in the input graphs. Bond dissociation enthalpies yielded the best improvement with a cosine similarity score of 0.462 relative to the baseline model (0.437). In this work we also apply dynamic graph attention which improves performance on benchmark problems and supports the inclusion of edge features. Between implementations, we investigate the nature of the molecular embedding for spectra prediction and discuss the recognition of fragment topographies in distinct chemistries for further development in tandem mass spectrometry prediction.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Surrogate modeling of Cellular-Potts agent-based models as a segmentation task using the U-Net neural network architecture

The Cellular-Potts model is a powerful and ubiquitous framework for developing computational models for simulating complex multicellular biological systems. Cellular-Potts models (CPMs) are often computationally expensive due to the explicit modeling of interactions among large numbers of individual model agents and diffusive fields described by partial differential equations (PDEs). In this work, we develop a convolutional neural network (CNN) surrogate model using a U-Net architecture that accounts for periodic boundary conditions. We use this model to accelerate the evaluation of a mechanistic CPM previously used to investigate in vitro vasculogenesis. The surrogate model was trained to predict 100 computational steps ahead (Monte-Carlo steps, MCS), accelerating simulation evaluations by a factor of 562 times compared to single-core CPM code execution on CPU. Over short timescales of up to 3 recursive evaluations, or 300 MCS, our model captures the emergent behaviors demonstrated by the original Cellular-Potts model such as vessel sprouting, extension and anastomosis, and contraction of vascular lacunae. This approach demonstrates the potential for deep learning to serve as a step toward efficient surrogate models for CPM simulations, enabling faster evaluation of computationally expensive CPM simulations of biological processes.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Extracting the Galactic Center excess’ source-count distribution with neural nets

The two leading hypotheses for the Galactic Center excess (GCE) in the Fermi data are an unresolved population of faint millisecond pulsars (MSPs) and dark-matter (DM) annihilation. The dichotomy between these explanations is typically reflected by modeling them as two separate emission components. However, point sources (PSs) such as MSPs become statistically degenerate with smooth Poisson emission in the ultrafaint limit (formally where each source is expected to contribute much less than one photon on average), leading to an ambiguity that can render questions such as whether the emission is PS-like or Poissonian in nature ill defined. We present a conceptually new approach that describes the PS and Poisson emission in a unified manner and only afterwards derives constraints on the Poissonian component from the so obtained results. For the implementation of this approach, we leverage deep learning techniques, centered around a neural network-based method for histogram regression that expresses uncertainties in terms of quantiles. We demonstrate that our method is robust against a number of systematics that have plagued previous approaches, in particular DM/PS misattribution. In the Fermi data, we find a faint GCE described by a median source-count distribution (SCD) peaked at a flux of ~ 4 x 10 -11 counts cm -2 s -1 (corresponding to ~ 3-4 expected counts per PS), which would require N ~ $\mathscr{O}$(10 4 ) sources to explain the entire excess (median value N = 29,300 across the sky). Although faint, this SCD allows us to derive the constraint η ρ ≤ 66% for the Poissonian fraction of the GCE flux η ρ at 95% confidence, suggesting that a substantial amount of the GCE flux is due to PSs.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗