Search NASA⌕ Search

SEARCH · Search NASA

Results for “training efficiency”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Deep Learning-based Parameterization of Complex 3D CO2 Saturation Data in Large-scale Geological Carbon Storage

In deep learning (DL), dimension reduction plays a pivotal role in improving training efficiency and minimizing overfitting, especially when working with complex datasets like three-dimensional (3D) saturation data. In the context of geological carbon storage (GCS), 3D saturation data introduces unique challenges due to its sparse nature and sharp transitions at plume boundaries, known as shock fronts. To tackle these challenges, we developed a novel DL framework that combines dimension reduction with advanced 3D reconstruction techniques. Our approach utilizes latent variables derived from 2D average saturation fields to efficiently capture the essential features of high-dimensional data while reducing the number of variables. This enhances both the robustness and accuracy of DL models, making the framework more practical for real-world applications. By offering a tailored solution for modeling complex 3D saturation dynamics, this framework holds significant potential for environmental monitoring, energy storage, and other geological applications.

Wang, Hongsheng [University of Texas at Austin]↗
DOE OSTI2025

Keeping LAMMPS cutting edge

Since its inception 30 years ago, LAMMPS has grown to be a world-class molecular dynamics code and a cornerstone of computational materials science research. This project aimed to keep LAMMPS at the forefront of molecular dynamics simulations by adapting LAMMPS to the latest developments in machine learning technology and hardware. Initially, the project set out to provide a unified implementation of active learning for efficient training data generation in LAMMPS, but the research trajectory pivoted to address more immediate and impactful opportunities. On the hardware side, recent record-breaking molecular dynamics simulations were developed on the Cerebras wafer-scale AI chip, and this project has developed an interface between LAMMPS and the hardware-specific molecular dynamics code to accelerate and simplify development and user adoption. On the software side, PyTorch’s Ahead-of-Time (AOT) compilation features promised increased performance for state-of-the-art equivariant neural network potentials, and this project laid the groundwork for their adoption in LAMMPS, resulting in a nearly 20x acceleration in extreme cases. Combined with a comprehensive benchmark study of LAMMPS across all current exascale systems, this project has reinforced LAMMPS’s role as a versatile, high-performance tool for current and future materials science applications.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Fast Adaptive Neural Control of Resonant Extraction at Fermilab

We present the development of a machine learning (ML) based regulation system for third-order resonant beam extraction in the Mu2e experiment at Fermilab. Classical and ML-based controllers have been optimized using semi-analytic simulations and evaluated in terms of regulation performance and training efficiency. We compare several controller architectures and discuss the integration of neural control into an adaptive framework. We also present progress on surrogate models that predict the controller response given a spill intensity and controller action history. To enable real-time deployment, we report progress on implementing low-latency, edge-based inference suitable for hardware-constrained environments. Our results demonstrate the feasibility and advantages of ML-based control in managing complex, time-varying physical systems, with broader implications for accelerator operations and other domains requiring fast, adaptive regulation.

Berlioz, Jose Rene [Fermilab]↗
DOE OSTI2022

Quantum Machine Learning with SQUID

In this work we present the Scaled QUantum IDentifier (SQUID), an open-source framework for exploring hybrid Quantum-Classical algorithms for classification problems. The classical infrastructure is based on PyTorch and we provide a standardized design to implement a variety of quantum models with the capability of back-propagation for efficient training. We present the structure of our framework and provide examples of using SQUID in a standard binary classification problem from the popular MNIST dataset. In particular, we highlight the implications for scalability for gradient-based optimization of quantum models on the choice of output for variational quantum models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Simulation of Electron-Proton Scattering Events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)

We apply generative adversarial network (GAN) technology to build an event generator that simulates particle production in electron-proton scattering that is free of theoretical assumptions about underlying particle dynamics. The difficulty of efficiently training a GAN event simulator lies in learning the complicated patterns of the distributions of the particles physical properties. We develop a GAN that selects a set of transformed features from particle momenta that can be generated easily by the generator, and uses these to produce a set of augmented features that improve the sensitivity of the discriminator. The new Feature-Augmented and Transformed GAN (FAT-GAN) is able to faithfully reproduce the distribution of final state electron momenta in inclusive electron scattering, without the need for input derived from domain-based theoretical assumptions. The developed technology can play a significant role in boosting the science of existing and future accelerator facilities, such as the Electron-Ion Collider.

Alanazi, Yasir↗
DOE OSTI2020

Robust Learning with Implicit Residual Networks

In this effort, we propose a new deep architecture utilizing residual blocks inspired by implicit discretization schemes. As opposed to the standard feed-forward networks, the outputs of the proposed implicit residual blocks are defined as the fixed points of the appropriately chosen nonlinear transformations. We show that this choice leads to the improved stability of both forward and backward propagations, has a favorable impact on the generalization power, and allows for control the robustness of the network with only a few hyperparameters. In addition, the proposed reformulation of ResNet does not introduce new parameters and can potentially lead to a reduction in the number of required layers due to improved forward stability. Finally, we derive the memory-efficient training algorithm, propose a stochastic regularization technique, and provide numerical results in support of our findings.

Reshniak, Viktor↗
DOE OSTI2020

Thermodynamic Consistent Neural Networks for Learning Material Interfacial Mechanics

For multilayer materials in thin substrate systems, interfacial failure is one of the most challenges. The traction-separation relations (TSR) quantitatively describe the mechanical behavior of a material interface undergoing openings, which is critical to understand and predict interfacial failures under complex loadings. However, existing theoretical models have limitations on enough complexity and flexibility to well learn the real-world TSR from experimental observations. A neural network can fit well along with the loading paths but often fails to obey the laws of physics, due to a lack of experimental data and understanding of the hidden physical mechanism. In this paper, we propose a thermodynamic consistent neural network (TCNN) approach to build a data-driven model of the TSR with sparse experimental data. The TCNN leverages recent advances in physics-informed neural networks (PINN) that encode prior physical information into the loss function and efficiently train the neural networks using automatic differentiation. We investigate three thermodynamic consistent principles, i.e., positive energy dissipation, steepest energy dissipation gradient, and energy conservative loading path. All of them are mathematically formulated and embedded into a neural network model with a novel defined loss function. A real-world experiment demonstrates the superior performance of TCNN, and we find that TCNN provides an accurate prediction of the whole TSR surface and significantly reduces the violated prediction against the laws of physics.

Zhang, Jiaxin↗
DOE OSTI2023

Advancing Energy Efficiency Through Workforce Training

This Final Technical Report summarizes the work done on to develop and implement the Energy Basics Training Tool with industry partners and the Pacific Northwest National Laboratory. This project leveraged existing infrastructure and content developed by DOE in the Building America Solution Center (BASC) and Building Science Education Solution Center (BSESC) to design model content sets for use in entry-level construction programs at the high school certificate, boot camp, and other entry level training programs.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

Phase Diagrams of Alloys and Their Hydrides via On-Lattice Graph Neural Networks and Limited Training Data

Efficient prediction of sampling-intensive thermodynamic properties is needed to evaluate material performance and permit high-throughput materials modeling for a diverse array of technology applications. To alleviate the prohibitive computational expense of high-throughput configurational sampling with density functional theory (DFT), surrogate modeling strategies like cluster expansion are many orders of magnitude more efficient but can be difficult to construct in systems with high compositional complexity. We therefore employ minimal-complexity graph neural network models that accurately predict and can even extrapolate to out-of-train distribution formation energies of DFT-relaxed structures from an ideal (unrelaxed) crystallographic representation. This enables the large-scale sampling necessary for various thermodynamic property predictions that may otherwise be intractable and can be achieved with small training data sets. Two exemplars, optimizing the thermodynamic stability of low-density high-entropy alloys and modulating the plateau pressure of hydrogen in metal alloys, demonstrate the power of this approach, which can be extended to a variety of materials discovery and modeling problems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

PANTHER: A Programmable Architecture for Neural Network Training Harnessing Energy-Efficient ReRAM

The wide adoption of deep neural networks has been accompanied by ever-increasing energy and performance demands due to the expensive nature of training them. Additionally, numerous special-purpose architectures have been proposed to accelerate training: both digital and hybrid digital-analog using resistive RAM (ReRAM) crossbars. ReRAM-based accelerators have demonstrated the effectiveness of ReRAM crossbars at performing matrix-vector multiplication operations that are prevalent in training. However, they still suffer from inefficiency due to the use of serial reads and writes for performing the weight gradient and update step. A few works have demonstrated the possibility of performing outer products in crossbars, which can be used to realize the weight gradient and update step without the use of serial reads and writes. However, these works have been limited to low precision operations which are not sufficient for typical training workloads. Moreover, they have been confined to a limited set of training algorithms for fully-connected layers only. To address these limitations, we propose a bit-slicing technique for enhancing the precision of ReRAM-based outer products, which is substantially different from bit-slicing for matrix-vector multiplication only. We incorporate this technique into a crossbar architecture with three variants catered to different training algorithms. To evaluate our design on different types of layers in neural networks (fully-connected, convolutional, etc.) and training algorithms, we develop PANTHER, an ISA-programmable training accelerator with compiler support. Our design can also be integrated into other accelerators in the literature to enhance their efficiency. Our evaluation shows that PANTHER achieves up to 8.02×, 54.21×, and 103× energy reductions as well as 7.16×, 4.02×, and 16× execution time reductions compared to digital accelerators, ReRAM-based accelerators, and GPUs, respectively.

42 ENGINEERING↗
DOE OSTI2020

Efficient I/O for Neural Network Training with Compressed Data

FanStore is a shared object store that enables efficient and scalable neural network training on supercomputers. By providing a global cache layer on node-local burst buffers using a compressed representation, it significantly enhances the processing capability of deep learning (DL) applications on existing hardware. In addition, FanStore allows POSIX-compliant file access to the compressed data in user space. We investigate the tradeoff between runtime overhead and data compression ratio using real-world datasets and applications, and propose a compressor selection algorithm to maximize storage capacity given performance constraints. We consider both asynchronous (i.e., with prefetching) and synchronous I/O strategies, and propose mechanisms for selecting compressors for both approaches. Using FanStore, the same storage hardware can host 2-13x more data for example applications without significant runtime overhead. Empirically, our experiments show that FanStore scales to 512 compute nodes with near linear performance scalability.

Zhang, Zhao↗
DOE OSTI2024

Optimizing Distributed Training on Frontier for Large Language Models

Large language models (LLMs) have demonstrated remarkable success as foundational models, benefiting various downstream applications through fine-tuning. Loss scaling studies have demonstrated the superior performance of larger LLMs compared to their smaller counterparts. Nevertheless, training LLMs with billions of parameters poses significant challenges and requires considerable computational resources. For example, training a one trillion parameter GPT-style model on 20 trillion tokens requires a staggering 120 million exaflops. This research explores efficient distributed training strategies to extract this computation from Frontier, the world's first exascale supercomputer. We enable and investigate various model and data parallel training techniques, such as tensor parallelism, pipeline parallelism, and sharded data parallelism, to facilitate training a trillion-parameter model on Frontier. We empirically assess these techniques and their associated parameters to determine their impact on memory footprint, communication latency, and GPU's computational efficiency. We analyze the complex interplay among these techniques and find a strategy to combine them to achieve high throughput through hyperparameter tuning. We have identified efficient strategies for training large LLMs of varying sizes through empirical analysis and hyperparameter tuning. For 22 Billion, 175 Billion, and 1 Trillion parameters, we achieved GPU throughputs of 38.38%, 36.14%, and 31.96%, respectively. For the training of the 175 Billion parameter model and the 1 Trillion parameter model, we achieved 100% weak scaling efficiency on 1024 and 3072 Mi250X GPUs, respectively. We also achieved strong scaling efficiencies of 89% and 87% for these two models. We trained these models only tens of iterations instead of training till completion.

Yin, Junqi↗
DOE OSTI2022

Efficient data acquisition and training of collisional-radiative model artificial neural network surrogates through adaptive parameter space sampling

Abstract Effective plasma transport modeling of magnetically confined fusion devices relies on having an accurate understanding of the ion composition and radiative power losses of the plasma. Generally, these quantities can be obtained from solutions of a collisional-radiative (CR) model at each time step within a plasma transport simulation. However, even compact, approximate CR models can be computationally onerous to evaluate, and in-situ evaluation of these models within a larger plasma transport code can lead to a rigid bottleneck. As a way to bypass this bottleneck, we propose deploying artificial neural network (ANN) surrogates to allow rapid evaluation of the necessary plasma quantities. However, one issue with training an accurate ANN surrogate is the reliance on a sufficiently large and representative training and validation data set, which can be time-consuming to generate. In this work we explore a data-driven active learning and training routine to allow autonomous adaptive sampling of the problem parameter space to ensure a sufficiently large and meaningful set of training data is assembled for the network training. As a result, we can demonstrate approximately order-of-magnitude savings in required training data samples to produce an accurate surrogate.

97 MATHEMATICS AND COMPUTING↗
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 OSTI2021

Enabling rapid COVID-19 small molecule drug design through scalable deep learning of generative models

We improved the quality and reduced the time to produce machine learned models for use in small molecule antiviral design. Our globally asynchronous multi-level parallel training approach strong scales to all of Sierra with up to 97.7% efficiency. We trained a novel, character-based Wasserstein autoencoder that produces a higher quality model trained on 1.613 billion compounds in 23 minutes while the previous state of the art takes a day on 1 million compounds. Reducing training time from a day to minutes shifts the model creation bottleneck from computer job turnaround time to human innovation time. Our implementation achieves 318 PFLOPs for 17.1% of half-precision peak. We will incorporate this model into our molecular design loop enabling the generation of more diverse compounds; searching for novel, candidate antiviral drugs improves and reduces the time to synthesize compounds to be tested in the lab.

Jacobs, Sam Ade↗
DOE OSTI2023

Utilizing multimodal high-intensity interval training for a firefighter training academy during the COVID-19 pandemic

Firefighters typically undergo a 16–24-week training academy during which they perform a variety of traditional exercise programs such as cardiovascular, resistance, and concurrent training. Because of limited facility access, some fire departments seek alternative exercise programs, such as multimodal high-intensity interval training (MM-HIIT), which essentially combines resistance and interval training. Here, the primary purpose of this study was to assess the effect of MM-HIIT on body composition and physical fitness in firefighter recruits who completed a training academy during the coronavirus (COVID-19) pandemic. A secondary purpose was to compare the effects of MM-HIIT to previous training academies that implemented traditional exercise programs. Healthy and recreationally-trained recruits (n=12) participated in 2-3 days/week of MM-HIIT for 12 weeks and had several components of body composition and physical fitness measured before and after the program. Because of COVID-19-related gym closures, all MM-HIIT sessions were performed outdoors at a fire station with minimal equipment. These data were retroactively compared to a control group (CG) that previously completed training academies with traditional exercise programs. Subjects in the MM-HIIT group significantly improved several components of body composition and fitness, including fat mass, fat-free mass, body fat percentage, aerobic capacity, and muscular endurance (p < 0.005). Moreover, there were no significant differences for any dependent variable when MM-HIIT was compared to the CG (p≥0.005). These results suggest that MM-HIIT may serve as an effective substitute for traditional concurrent training paradigms that are typically used for firefighter academies.

60 APPLIED LIFE SCIENCES↗