Search NASA⌕ Search

SEARCH · Search NASA

Results for “DNN operators”

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 OSTI2022

Throughput-Oriented and Accuracy-Aware DNN Training with BFloat16 on GPU

Deep Neural Networks (DNNs) have transformed the field of artificial intelligence and achieved extraordinary success in many areas. The training of DNNs is commonly compute and memory-intensive, which has resulted in several optimizations in the training phase. Among them, reduced precision is a typical and widely used technique to accelerate DNN training and reduce memory requirements. However, applying a widely adopted reduced precision format such as Float16 to all involved operations in DNN training is not optimal as the use of Float16 in some operations can hurt model accuracy. Meanwhile, additional optimizations including loss scaling and autocast techniques can mitigate the accuracy loss but lead to inherent overhead and inadequate use of reduced precision. In this work, we leverage another reduced precision format, BFloat16, and introduce a throughput-oriented and accuracy-aware approach to maximize the performance potential of DNN training. Since the high throughput provided by BFloat16 format is accompanied by low precision of the floating-point representation, this approach achieves high throughput by using BFloat16 on all DNN operations and avoids the accuracy loss through a customized accuracy-aware normalization. Results show that our approach outperforms the state-of-the-art mixed-precision training by 1.21x on an NVIDIA A100 GPU.

Xie, Zhen↗
DOE OSTI2024

Evaluating Operators in Deep Neural Networks for Improving Performance Portability of SYCL

SYCL is a portable programming model for heterogeneous computing, so it is important to obtain reasonable performance portability of SYCL. Towards the goal of better understanding and improving performance portability of SYCL for machine learning workloads, we have been developing benchmarks for basic operators in deep neural networks (DNNs). These operators could be offloaded to heterogeneous computing devices such as graphics processing units (GPUs) to speed up computation. In this work, we introduce the benchmarks, evaluate the performance of the operators on GPU-based systems, and describe the causes of the performance gap between the SYCL and Compute Unified Device Architecture (CUDA) kernels. We find that the causes are related to the utilization of the texture cache for read-only data, optimization of the memory accesses with strength reduction, shared local memory accesses, and register usage per thread. We hope that the efforts of developing benchmarks for studying performance portability will stimulate discussion and interactions within the community.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Bayesian reduced-order deep learning surrogate model for dynamic systems described by partial differential equations

We propose a reduced-order deep-learning surrogate model for dynamic systems described by time-dependent partial differential equations. This method employs space–time Karhunen–Loève expansions (KLEs) of the state variables and space-dependent KLEs of space-varying parameters to identify the reduced (latent) dimensions. Subsequently, a deep neural network (DNN) is used to map the parameter latent space to the state variable latent space. An approximate Bayesian method is developed for uncertainty quantification (UQ) in the proposed KL-DNN surrogate model. The KL-DNN method is tested for the linear advection–diffusion and nonlinear diffusion equations, and the Bayesian approach for UQ is compared with the deep ensembling (DE) approach, commonly used for quantifying uncertainty in DNN models. It was found that the approximate Bayesian method provides a more informative distribution of the PDE solutions in terms of the coverage of the reference PDE solutions (the percentage of nodes where the reference solution is within the confidence interval predicted by the UQ methods) and log predictive probability. The DE method is found to underestimate uncertainty and introduce bias. For the nonlinear diffusion equation, we compare the KL-DNN method with the Fourier Neural Operator (FNO) method and find that KL-DNN is 10% more accurate and needs less training time than the FNO method.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

MIND-MAC: Multi-Level In-memory Quasi Non-Destructive MAC Operation in Compact 2T-nC FeRAM for Efficient DNN Accelerator

We present MIND-MAC, a compact 2T-nC FeRAM architecture that performs multi-level, quasi-non-destructive in-memory multiply–accumulate (MAC) for deep neural networks. By exploiting voltage-controlled partial domain switching in MFM capacitors and read-transistor amplification, the cell stores multi-bit weights and gates bit-serial inputs to produce an accumulated current on shared lines. We combine TCAD-extracted parasitics with experimentally calibrated ferroelectric models in SPICE to validate device-/circuit-level behavior, and validate multi-level sensing and QNRO with measurements on a fabricated 2T-3C test vehicle. An analytical system model maps MIND-MAC to a 6-GB main-memory in-memory compute (IMC) architecture and benchmarks VGG13 inference in 61.08 ms at 964.99 mJ. Results indicate high density, reduced rewrite overhead, and energy efficiency, positioning 2T-nC FeRAM as a promising IMC candidate for next-generation AI hardware.

36 MATERIALS SCIENCE↗
DOE OSTI2020

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.

Guan, Hui↗
DOE OSTI2021

Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators

It is widely known that neural networks (NNs) are universal approximators of continuous functions. However, a less known but powerful result is that a NN with a single hidden layer can accurately approximate any nonlinear continuous operator. This universal approximation theorem of operators is suggestive of the structure and potential of deep neural networks (DNNs) in learning continuous operators or complex systems from streams of scattered data. Here, in this work, we thus extend this theorem to DNNs. We design a new network with small generalization error, the deep operator network (DeepONet), which consists of a DNN for encoding the discrete input function space (branch net) and another DNN for encoding the domain of the output functions (trunk net). We demonstrate that DeepONet can learn various explicit operators, such as integrals and fractional Laplacians, as well as implicit operators that represent deterministic and stochastic differential equations. We study different formulations of the input function space and its effect on the generalization error for 16 different diverse applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Deep neural network improves the estimation of polygenic risk scores for breast cancer

Polygenic risk scores (PRS) estimate the genetic risk of an individual for a complex disease based on many genetic variants across the whole genome. Here, we compared a series of computational models for estimation of breast cancer PRS. A deep neural network (DNN) was found to outperform alternative machine learning techniques and established statistical algorithms, including BLUP, BayesA, and LDpred. In the test cohort with 50% prevalence, the Area Under the receiver operating characteristic Curve (AUC) were 67.4% for DNN, 64.2% for BLUP, 64.5% for BayesA, and 62.4% for LDpred. BLUP, BayesA, and LPpred all generated PRS that followed a normal distribution in the case population. However, the PRS generated by DNN in the case population followed a bimodal distribution composed of two normal distributions with distinctly different means. This suggests that DNN was able to separate the case population into a high-genetic-risk case subpopulation with an average PRS significantly higher than the control population and a normal-genetic-risk case subpopulation with an average PRS similar to the control population. This allowed DNN to achieve 18.8% recall at 90% precision in the test cohort with 50% prevalence, which can be extrapolated to 65.4% recall at 20% precision in a general population with 12% prevalence. Interpretation of the DNN model identified salient variants that were assigned insignificant p values by association studies, but were important for DNN prediction. These variants may be associated with the phenotype through nonlinear relationships.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Data-Driven Affinely Adjustable Robust Volt/VAr Control

Recent years have seen the increasing proliferation of distributed energy resources with intermittent power outputs, posing new challenges to the voltage management in distribution networks. To this end, this paper proposes a data-driven affinely adjustable robust Volt/VAr control (AARVVC) scheme, which modulates the smart inverter’s reactive power in an affine function of its active power, based on the voltage sensitivities with respect to real/reactive power injections. To achieve a fast and accurate estimation of voltage sensitivities, we propose a data-driven method based on deep neural network (DNN), together with a rule-based bus-selection process using the bidirectional search method. Our method only uses the operating statuses of selected buses as inputs to DNN, thus significantly improving the training efficiency and reducing information redundancy. Finally, a distributed consensus-based solution, based on the alternating direction method of multipliers (ADMM), for the AARVVC is applied to decide the inverter’s reactive power adjustment rule with respect to its active power. Only limited information exchange is required between each local agent and the central agent to obtain the slope of the reactive power adjustment rule, and there is no need for the central agent to solve any (sub)optimization problems. Finally, numerical results on the modified IEEE-123 bus system validate the effectiveness and superiority of the proposed data-driven AARVVC method.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

A Deep Neural Network for Accurate and Robust Prediction of the Glass Transition Temperature of Polyhydroxyalkanoate Homo- and Copolymers

The purpose of this study was to develop a data-driven machine learning model to predict the performance properties of polyhydroxyalkanoates (PHAs), a group of biosourced polyesters featuring excellent performance, to guide future design and synthesis experiments. A deep neural network (DNN) machine learning model was built for predicting the glass transition temperature, Tg, of PHA homo- and copolymers. Molecular fingerprints were used to capture the structural and atomic information of PHA monomers. The other input variables included the molecular weight, the polydispersity index, and the percentage of each monomer in the homo- and copolymers. The results indicate that the DNN model achieves high accuracy in estimation of the glass transition temperature of PHAs. In addition, the symmetry of the DNN model is ensured by incorporating symmetry data in the training process. The DNN model achieved better performance than the support vector machine (SVD), a nonlinear ML model and least absolute shrinkage and selection operator (LASSO), a sparse linear regression model. The relative importance of factors affecting the DNN model prediction were analyzed. Sensitivity of the DNN model, including strategies to deal with missing data, were also investigated. Compared with commonly used machine learning models incorporating quantitative structure–property (QSPR) relationships, it does not require an explicit descriptor selection step but shows a comparable performance. The machine learning model framework can be readily extended to predict other properties.

quantitative structure–property relationship (QSPR↗
DOE OSTI2025

Karhunen–Loève deep learning method for surrogate modeling and approximate Bayesian parameter estimation

We evaluate the performance of the Karhunen-Loève Deep Neural Network (KL-DNN) framework for surrogate modeling and approximate Bayesian parameter estimation in partial differential equation models. In the surrogate model, the Karhunen-Loève (KL) expansions are used for the dimensionality reduction of the number of unknown parameters and variables, and a deep neural network is employed to relate the reduced space of parameters to that of the state variables. The KL-DNN surrogate model is used to formulate a maximum-a-posteriori-like least-squares problem, which is randomized to draw samples of the posterior distribution of the parameters. We test the proposed framework for a hypothetical unconfined aquifer via comparison with the forward MODFLOW and inverse PEST++ iterative ensemble smoother (IES) solutions as well as the state-of-the-art Fourier neural operator (FNO) and deep operator networks (DeepONets) operator learning surrogate models. Our results show that the KL-DNN surrogate model outperforms FNO and DeepONet for forward predictions. For solving inverse problems, the randomized algorithm provides the same or more accurate Bayesian predictions of the parameters than IES as evidenced by the higher log-predictive probability of both the estimated parameter field and the forecast hydraulic head. The posterior mean obtained from the randomized algorithm is closer to the reference parameter field than that obtained with FNO as the maximum a posteriori estimate.

Approximate Bayesian inference↗
DOE OSTI2022

DNN-based policies for stochastic AC OPF

We report a prominent challenge to the safe and optimal operation of the modern power grid arises due to growing uncertainties in loads and renewables. Stochastic optimal power flow (SOPF) formulations provide a mechanism to handle these uncertainties by computing dispatch decisions and control policies that maintain feasibility under uncertainty. Most SOPF formulations consider simple control policies such as affine policies that are mathematically simple and resemble many policies used in current practice. Motivated by the efficacy of machine learning (ML) algorithms and the potential benefits of general control policies for cost and constraint enforcement, we put forth a deep neural network (DNN)-based policy that predicts the generator dispatch decisions in real time in response to uncertainty. The weights of the DNN are learnt using stochastic primal–dual updates that solve the SOPF without the need for prior generation of training labels and can explicitly account for the feasibility constraints in the SOPF. The advantages of the DNN policy over simpler policies and their efficacy in enforcing safety limits and producing near optimal solutions are demonstrated in the context of a chance constrained formulation on a number of test cases.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2021

Advancing Fissile Materials Production Modeling with Adaptive Computing Environment and Simulations (ACES)

The Department of Energy’s National Nuclear Security Administration (DOE/NNSA) provides advanced capabilities to simulate the uranium enrichment process to support international negotiations on the peaceful use of nuclear energy. Uranium isotope separation centrifuges connected in a cascade configuration can produce the low-enriched uranium needed for nuclear power. However, those same centrifuges connected in a different configuration can also produce highly enriched uranium for nuclear weapons. Having the capability to assess cascade operations and identify nefarious activities promotes the peaceful uses of nuclear energy while restricting nuclear weapons proliferation. DNN R&D's Nonproliferation Stewardship Program Adaptive Computing Environment and Simulations (ACES) project is creating a modern, sustainable ecosystem of physics-based models and data-analytics tools that enables analysts to model uranium enrichment systems, simulate operational scenarios, and apply various policy options to explore potential outcomes.

07 ISOTOPE AND RADIATION SOURCES↗
DOE OSTI2025

A hybrid numerical and machine learning framework for evaluating the performance of a 780 cm 2 aqueous organic redox flow battery

Aqueous organic redox flow battery (AORFB) is a promising cost-competitive technology for large-scale energy storage. Among existing work, the dihydroxyphenazine (DHP)-based AORFB has demonstrated high energy density and low capacity degradation in 10 cm2 cells during lab tests. However, its commercial-scale performance in more complex environments remains unknown, posing a barrier for commercialization. To address this gap, this work presents a comprehensive performance evaluation of a 780 cm 2 DHP-based AORFB by combining physics-based numerical model, machine learning (ML)-based surrogate models, and ML-derived sensitivity quantification. Specifically, we first select 12 key battery parameters that include 10 physicochemical quantities and 2 operation quantities, then select 6 performance metrics that include energy efficiency (EE), discharging capacity, charging energy, and power losses due to concentration, activation, and ohmic over-potentials. With such selection, 12800 combinations of the 12 parameters are subsequently generated using the Latin Hypercube Sampling method. These combinations, together with 38 pre-defined State of Charge, are then integrated to a validated AORFB model developed in COMSOL to compute the performance metrics. With both input parameters and performance metrics, 60 deep neural network (DNN) surrogate models are then trained to approximate the relationship between the 10 physicochemical quantities and 6 performance metrics at each flow rate and current density. Sensitivity scores are then calculated based on the DNN models. Two additional sensitivity analysis tools, i.e., MARS, and SHAP, are also used to cross-validate the sensitivity scores from the DNN. The results demonstrate that 1) the standard potential ranks the first in controlling EE and charging energy, 2) the membrane conductivity is most critical for power loss and EE, and 3) specific area and reaction rate control activation power loss.

25 ENERGY STORAGE↗
DOE OSTI2023

Fast and accurate reduced-order modeling of a MOOSE-based additive manufacturing model with operator learning

One predominant challenge in additive manufacturing (AM) is to achieve specific material properties by manipulating manufacturing process parameters during the runtime. Such manipulation tends to increase the computational load imposed on existing simulation tools employed in AM. The goal of the present work is to construct a fast and accurate reduced-order model (ROM) for an AM model developed within the Multiphysics Object-Oriented Simulation Environment (MOOSE) framework, ultimately reducing the time/cost of AM control and optimization processes. Our adoption of the operator learning (OL) approach enabled us to learn a family of differential equations produced by altering process variables in the laser’s Gaussian point heat source. More specifically, we used the Fourier neural operator (FNO) and deep operator network (DeepONet) to develop ROMs for time-dependent responses. Furthermore, we benchmarked the performance of these OL methods against a conventional deep neural network (DNN)-based ROM. Ultimately, we found that OL methods offer comparable performance and, in terms of accuracy and generalizability, even outperform DNN at predicting scalar model responses. The DNN-based ROM afforded the fastest training time. Furthermore, all the ROMs were faster than the original MOOSE model yet still provided accurate predictions. FNO had a smaller mean prediction error than DeepONet, with a larger variance for time-dependent responses. Unlike DNN, both FNO and DeepONet were able to simulate time series data without the need for dimensionality reduction techniques. Finally, the present work can help facilitate the AM optimization process by enabling faster execution of simulation tools while still preserving evaluation accuracy.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Measurement of a radial flow profile with eddy current flow meters and deep neural networks

Eddy current flow meters (ECFMs) measure flows of conductive fluids. Recent interest in ECFMs has increased due to applications in advanced nuclear reactors. ECFMs are well suited for such applications, as they can provide non-invasive measurements of flow in fluids that are often difficult to measure. Traditionally, ECFMs are operated using an alternating current at a single frequency, limiting ECFMs to measure average fluid velocities, blockages, or voids. Here, we expand the capabilities of ECFMs by measuring the fluid radial velocity profile of liquid mercury. To accomplish this, we made several ECFM sensitivity measurements at a range of frequencies. Different frequencies vary the electromagnetic skin depth of the device. By adjusting frequencies, we probed the fluid velocity at various radial locations and constructed a flow-velocity profile. The relationship between the ECFM measurements and velocity profile is nonlinear and requires solving an inverse problem. Using electromagnetic finite-element simulations to train a deep neural network (DNN), we created a model that provides a stable general relationship between the sensitivity measurements of an ECFM and the fluid velocity profile. Using ECFM measurements of liquid mercury, our DNN model calculates a flow profile that agrees well with computational fluid dynamics (CFD) simulations. This technique has potential to improve flow monitoring for optimization, safe operation of conductive fluid loops, and/or validating complex CFD models.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Resistive Switching of Spinel Li 4 Ti 5 O 12 Lithium-Ion Battery Material for Neuromorphic Computing

The rapid rise of AI has exposed significant limitations in conventional Von Neumann computing architecture, particularly in regard to speed and energy efficiency. To address these challenges, researchers are exploring a brain-inspired neuromorphic architecture that mimics biological neural networks, enabling massive parallel processing with reduced power consumption for complex AI computational demands. Recent interest has focused on utilizing battery electrodes and solid electrolyte materials for their resistive switching properties in developing a neuromorphic architecture. These properties are precisely tuned through local- and bulk-level chemical composition modifications via voltage bias stimuli. In this study, we demonstrate fabricating a three-terminal lithium-ion electrochemical transistor based on lithium titanium oxide (Li 4 Ti 5 O 12 ), a popular lithium-ion battery anode material. We deposited and characterized LTO thin films using RF sputtering, demonstrating a 6 orders of magnitude increase in electronic conductivity upon lithiation, with conductivity plateauing after 20% lithiation. Density functional theory calculations revealed transformation from the insulating to conducting state, supported by experimental characterization through X-Ray Photoelectron Spectroscopy (XPS) and Direct Current (DC) polarization analyses. The fabricated transistor consisted of LTO as the channel layer, gold as source/drain terminals, lithium phosphorus oxynitride (LiPON) as the lithium-ion conductor, and copper as the gate terminal. The device exhibited clear hysteresis in transfer characteristics due to lithium insertion/extraction processes. Long-term potentiation (LTP) and long-term depression (LTD) measurements showed an asymmetric ratio of 1.425 and maximum/minimum conductance ratio of 7.83. When implemented in a deep neural network (DNN) for MNIST handwritten digit recognition, the device achieved 92.03% accuracy over 20 training epochs. Detailed transport mechanism analysis revealed the crucial role of oxygen vacancies and interface effects in device operation. Our preliminary findings establish LTO-based lithium-ion electrochemical transistors as promising candidates for energy-efficient neuromorphic computing applications, offering potential solutions to traditional Von Neumann architecture limitations.

25 ENERGY STORAGE↗
DOE OSTI2025

LUNA: LUT-Based Neural Architecture for Fast and Low-Cost Qubit Readout

Qubit readout is a critical operation in quantum computing systems, which maps the analog response of qubits into discrete classical states. Deep neural networks (DNNs) have recently emerged as a promising solution to improve readout accuracy . Prior hardware implementations of DNN-based readout are resource-intensive and suffer from high inference latency, limiting their practical use in low-latency decoding and quantum error correction (QEC) loops. This paper proposes LUNA, a fast and efficient superconducting qubit readout accelerator that combines low-cost integrator-based preprocessing with Look-Up Table (LUT) based neural networks for classification. The architecture uses simple integrators for dimensionality reduction with minimal hardware overhead, and employs LogicNets (DNNs synthesized into LUT logic) to drastically reduce resource usage while enabling ultra-low-latency inference. We integrate this with a differential evolution based exploration and optimization framework to identify high-quality design points. Our results show up to a 10.95x reduction in area and 30% lower latency with little to no loss in fidelity compared to the state-of-the-art. LUNA enables scalable, low-footprint, and high-speed qubit readout, supporting the development of larger and more reliable quantum computing systems.

Farooq, M. A. [Arizona State U., Tempe]↗
DOE OSTI2020

Physics-Informed Deep Neural Network Method for Limited Observability State Estimation

The precise knowledge regarding the state of the power grid is important in order to ensure optimal and reliable grid operation. Specifically, knowing the state of the distribution grid becomes increasingly important as more renewable energy sources are connected directly into the distribution network, increasing the fluctuations of the injected power. In this paper, we consider the case when the distribution grid becomes partially observable, due to for example cyber attacks, and the state estimation problem is under-determined. We present a new methodology that leverages a deep neural network (DNN) to estimate the grid state. The standard DNN training method is modified to explicitly incorporate the physical information of the grid topology and line/shunt admittance. We show that our method leads to a superior accuracy of the estimation when compared to the case when no physical information is provided. Finally, we compare the performance of our method to the standard state estimation approach, which is based on the weighted least squares with pseudo-measurements, and show that our method performs significantly better with respect to the estimation accuracy.

24 POWER TRANSMISSION AND DISTRIBUTION↗