Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning 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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
NASA NTRS1995

Locomotion training of legged robots using hybrid machine learning techniques

In this study artificial neural networks and fuzzy logic are used to control the jumping behavior of a three-link uniped robot. The biped locomotion control problem is an increment of the uniped locomotion control. Study of legged locomotion dynamics indicates that a hierarchical controller is required to control the behavior of a legged robot. A structured control strategy is suggested which includes navigator, motion planner, biped coordinator and uniped controllers. A three-link uniped robot simulation is developed to be used as the plant. Neurocontrollers were trained both online and offline. In the case of on-line training, a reinforcement learning technique was used to train the neurocontroller to make the robot jump to a specified height. After several hundred iterations of training, the plant output achieved an accuracy of 7.4%. However, when jump distance and body angular momentum were also included in the control objectives, training time became impractically long. In the case of off-line training, a three-layered backpropagation (BP) network was first used with three inputs, three outputs and 15 to 40 hidden nodes. Pre-generated data were presented to the network with a learning rate as low as 0.003 in order to reach convergence. The low learning rate required for convergence resulted in a very slow training process which took weeks to learn 460 examples. After training, performance of the neurocontroller was rather poor. Consequently, the BP network was replaced by a Cerebeller Model Articulation Controller (CMAC) network. Subsequent experiments described in this document show that the CMAC network is more suitable to the solution of uniped locomotion control problems in terms of both learning efficiency and performance. A new approach is introduced in this report, viz., a self-organizing multiagent cerebeller model for fuzzy-neural control of uniped locomotion is suggested to improve training efficiency. This is currently being evaluated for a possible patent by NASA, Johnson Space Center. An alternative modular approach is also developed which uses separate controllers for each stage of the running stride. A self-organizing fuzzy-neural controller controls the height, distance and angular momentum of the stride. A CMAC-based controller controls the movement of the leg from the time the foot leaves the ground to the time of landing. Because the leg joints are controlled at each time step during flight, movement is smooth and obstacles can be avoided. Initial results indicate that this approach can yield fast, accurate results.

Simon, William E.↗
NASA NTRS2004

Lab on a Chip Application Development for Exploration

At Marshall Space Flight Center a new capability has been established to aid the advancement of microfluidics for space flight monitoring systems. Lab-On-a-Chip Application Development (LOCAD) team has created a program for advancing Technology Readiness Levels (TRL) of 1 & 2 to TRL 6 and 7, quickly and economically for Lab-On-a-Chip (LOC) applications. Scientists and engineers can utilize LOCAD's process to efficiently learn about microfluidics and determine if microfluidics is applicable to their needs. Once the applicability has been determined, LOCAD can then perform tests to develop the new fluidic protocols which are different from macro-scale chemical reaction protocols. With this information new micro-devices can be created such as the development of a microfluidic system to aid in the search for life, past and present, on Mars. Particular indicators in the Martian soil can contain the direct evidence of life. But to extract the information from the soil and present it to the proper detectors requires multiple fluidic/chemical operations. This is where LOCAD is providing its unique abilities.

Monaco, Lisa↗
NASA NTRS2004

Lab-On-a-Chip Application Development (LOCAD): Bridging Technology Readiness for Exploration

At Marshall Space Flight Center we have established a capability to investigate the use of microfluidics for space flight. The Lab-On-a-Chip Application Development (LOCAD) team has created a program for advancing Technology Readiness Levels (TRL) of 1 and 2 to TRL 6 and 7, quickly and economically for Lab-On-a-Chip (LOC) applications. Scientists and engineers can utilize LOCAD'S process to efficiently learn about microfluidics and determine if microfluidics is applicable to their needs. Once the applicability has been determined, LOCAD can then perform tests to develop the new fluidic protocols which are different from macro-scale chemical reaction protocols. With this information new micro-fluidic devices can be created and tested. Currently, LOCAD is focused on using microfluidics for both Environmental Monitoring & Control, and Medical Systems. Eventually, handheld portable units utilizing LOC technology will perform rapid tests to determine water quality, and microbial contamination levels. Since LOC technology is drastically reduced in physical size, it thereby reduces power, weight, volume, and sample requirements, a big advantage considering the resource constraints associated with spaceflight. Another one of LOCAD's current activities is the development of a microfluidic system to aid in the search for life on Mars.

Spearing, Scott F.↗
DOE OSTI2021

Constrained Block Nonlinear Neural Dynamical Models

Neural network modules conditioned by known priors can be effectively trained and combined to represent systems with nonlinear dynamics. This work explores a novel formulation for data-efficient learning of deep control-oriented nonlinear dynamical models by embedding local model structure and constraints. The proposed method consists of neural network blocks that represent input, state, and output dynamics with constraints placed on the network weights and system variables. For handling partially observable dynamical systems, we utilize a state observer neural network to estimate the states of the system's latent dynamics. We evaluate the performance of the proposed architecture and training methods on system identification tasks for three nonlinear systems: a continuous stirred tank reactor, a two tank interacting system, and an aerodynamics body. Models optimized with a few thousand system state observations accurately represent system dynamics in open loop simulation over thousands of time steps from a single set of initial conditions. Experimental results demonstrate an order of magnitude reduction in open-loop simulation mean squared error for our constrained, block-structured neural models when compared to traditional unstructured and unconstrained neural network models.

Skomski, Elliott↗
DOE OSTI2020

The organic redox transistor for neuromorphic computing

Inspired by the in-memory computing architectures of biological systems, neuromorphic computing using crossbar arrays of artificial synapses based on non-volatile memory (NVM) devices with variable conductances has emerged as a new paradigm to enable massively parallel and ultra-low power computing hardware for data centric applications. Although inference has been demonstrated successfully using crossbars based on a variety of NMV technologies, efficient learning and scaling to large arrays (>10 6 elements) remains a challenge due to the synaptic elements' non-ideal electrical characteristics which degrades ANN accuracy. A further challenge is that in the conductive state memristors draw large currents >μA resulting in significant voltage drops in the interconnect wires and increased probability of failure in scaled arrays. We suggest the organic polymer redox transistor (RT) is an alternate approach that could solve many of these challenges, enabling both inference and parallel outer product updates, as recently demonstrated by Fuller et al. An RT consists of redox-active channel and gate electrodes in contact with a liquid or solid electrolyte. lon insertion through the electrolyte controls the channel electronic conductivity, while electron transfer through an external circuit maintains overall charge neutrality. Unlike a rechargeable battery, in the RT the voltage built-up across the electrolyte is kept to a minimum (typically <100 mV) by using the same material for the gate and channel. Elimination of the voltage offset simplifies integration of the RT into programmable arrays by enabling the use of various selectors. RTs based on inorganic and organic materials have been recently demonstrated with conductance tuning occurring at potentials of just a few mV and hundreds to thousands of linearly and symmetrically programmable conductance states, enabling near ideal accuracy in neural network simulations. Introduced in the 1980's, redox transistors with metallic gate electrodes and organic channel materials, also known as organic electrochemical transistors (OECTs), have been explored for a variety of applications such as chem- and bio-sensing, neural interfaces, and low cost printed circuits. A typical channel material for OECTs is the conducting polymer poly(3,4-ethylenedioxythiophene) doped with poly(styrene sulfonate) (PEDOT:PSS). PEDOT is a p-type semiconducting polymer with mobile positively charged polarons that hop chain-to-chain.

Talin, Albert Alec↗
DOE OSTI2022

Green Computing Catalyzer Kickoff: Green Artificial Intelligence (AI) Directions

For the 2022 JISEA annual meeting, JISEA introduces in this presentation the new Green Computing Catalyzer. The new catalyzer looks to establish green computing as a salient research domain at NREL, and crucially, to begin to address the looming computing energy crisis. The presentation provides some basic numbers, establishing energy use and source or carbon emissions for computing. The presentation also includes a brief history of green computing at NREL, empirical deep learning efficiency study, and research directions.

AI efficiency↗
DOE OSTI2024

Intricate short-range order in GeSn alloys revealed by atomistic simulations with highly accurate and efficient machine-learning potentials

GeSn alloys hold promise for silicon-compatible integrated applications in electronics, photonics, and topological quantum devices. However, understanding their intricate structures using density functional theory (DFT) calculations is hindered by spatiotemporal constraints. To overcome this limitation, we develop highly accurate and efficient machine-learning interatomic potentials based on a neuroevolution potential approach with farthest point sampling on a comprehensive DFT data set. The application of the developed machine-learning potential in large-scale atomistic simulations bridges the spatiotemporal gap between modeling and advanced characterizations, and facilitates the discovery of structural intricacies in GeSn alloys. Through extensive statistical sampling, we identify a type of short-range order (SRO) that is distinguished by both its structural signature and electronic band gap from the SRO structure previously predicted. Modeling based on a large simulation cell reveals the coexistence of nano SRO domains with various degrees of ordering, demonstrating a complex spatial heterogeneity of SRO structure. Finally, our study not only reinforces the significance of fine-level structural information in alloys, but it also constitutes an effective framework for exploring SRO in a broad range of complex alloys based on highly accurate and effective machine-learning potentials.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Predicting the Impact of Utility Lighting Rebate Programs on Promoting Industrial Energy Efficiency: A Machine Learning Approach

Implementation costs are a major factor in manufacturers’ decisions to invest in energy-efficient technologies. Emerging technologies in lighting systems, however, typically require small investment costs and offer short, simple payback periods, due, in part, to federal, state, and utility incentive programs. Recently, however, certain state and federal mandates have reduced the support for and efficacy of electricity utility incentivizing programs. To determine the impact of such support programs, this study examined historical data regarding lighting retrofit savings, implementation costs, and utility rebates gathered from 13 years of industrial energy audits by a U.S. Department of Energy Industrial Assessment Center in a midwestern state. It uses a machine learning approach to evaluate the industrial energy and cost-saving opportunities that may have been lost due to decisions attributable to legislative mandates, utility policies, and manufacturers’ calculations and to evaluate the potential effect of lighting rebates on manufacturers’ decisions to implement industrial energy-efficient lighting retrofits. The results indicate that the decision not to implement lighting energy efficiency recommendations resulted in a loss of more than USD800,000 in potential rebates by industries during the study period and that the implementation of lighting energy assessment recommendations could have increased by about 50% if electric utility rebates had been available. These findings can help industries evaluate the benefits of implementing lighting efficiency improvements, and help utilities determine feasible lighting retrofit rebate values for incentivizing such changes by the industries they serve.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Using machine learning to improve efficiency and accuracy of burnup measurements at PBR reactors [Slides]

The outline of the slides include: Motivations of the work; Modeling and simulation; Machine learning model; Results and comparison study with linear regression; and Conclusions. This work was done to help PBR designers and operators understand the burnup measurement better. We look forward to discussing the results in detail with industrial collaborators.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2026

Hierarchical Reinforcement Learning of a Short-Range Bond-Order Potential for Silica: Analytic Embedding of Coordination with Classical Efficiency

Reinforcement learning (RL) has recently emerged as a data-efficient strategy to parametrize short-range interatomic potentials. Building on our past RL optimization of pairwise silica models, we extend the framework to a bond-order (Tersoff-type) potential that provides an analytic embedding of local coordination through a three-body term. A hierarchical RL workflow combining continuous-action Monte Carlo Tree Search and property-based rewards efficiently explores the 26-dimensional parameter space, sequentially optimizing lattice parameters, densities, angles, and cohesive energies of 21 silica polymorphs. The resulting models, Q-Tersoff and ML-Tersoff, reproduce the energetic ordering of low-energy phases and capture the angular correlations and amorphous structure factors of silica with improved fidelity over pairwise force fields, while remaining orders of magnitude faster than high-dimensional machine-learned potentials. Both models underperform for elastic constants and high-energy frameworks, delineating the limits of the current analytic form. The approach establishes a general and interpretable route to angle-aware, short-range potentials that bridge physics-based and machine-learned descriptions of silicate materials.

36 MATERIALS SCIENCE↗
DOE OSTI2021

A machine learning approach for efficient multi-dimensional integration

Many physics problems involve integration in multi-dimensional space whose analytic solution is not available. The integrals can be evaluated using numerical integration methods, but it requires a large computational cost in some cases, so an efficient algorithm plays an important role in solving the physics problems. We propose a novel numerical multi-dimensional integration algorithm using machine learning (ML). After training a ML regression model to mimic a target integrand, the regression model is used to evaluate an approximation of the integral. Then, the difference between the approximation and the true answer is calculated to correct the bias in the approximation of the integral induced by ML prediction errors. Because of the bias correction, the final estimate of the integral is unbiased and has a statistically correct error estimation. Three ML models of multi-layer perceptron, gradient boosting decision tree, and Gaussian process regression algorithms are investigated. The performance of the proposed algorithm is demonstrated on six different families of integrands that typically appear in physics problems at various dimensions and integrand difficulties. The results show that, for the same total number of integrand evaluations, the new algorithm provides integral estimates with more than an order of magnitude smaller uncertainties than those of the VEGAS algorithm in most of the test cases.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

General Multifidelity Surrogate Models: Framework and Active-Learning Strategies for Efficient Rare Event Simulation

Estimating the probability of failure for complex real-world systems using high-fidelity computational models is often prohibitively expensive, especially when the probability is small. Exploiting low-fidelity models can make this process more feasible, but merging information from multiple low-fidelity and high-fidelity models poses several challenges. Here, this paper presents a robust multi-fidelity surrogate modeling strategy in which the multi-fidelity surrogate is assembled using an active learning strategy using an on-the-fly model adequacy assessment set within a subset simulation framework for efficient reliability analysis. The multi-fidelity surrogate is assembled by first applying a Gaussian process correction to each low-fidelity model and assigning a model probability based on the model's local predictive accuracy and cost. Three strategies are proposed to fuse these individual surrogates into an overall surrogate model based on model averaging and deterministic/stochastic model selection. The strategies also dictate which model evaluations are necessary. No assumptions are made about the relationships between low-fidelity models, while the high-fidelity model is assumed to be the most accurate and most computationally expensive model. Through two analytical and two numerical case studies, including a case study evaluating the failure probability of Tristructural isotropic-coated (TRISO) nuclear fuels, the algorithm is shown to be highly accurate while drastically reducing the number of high-fidelity model calls (and hence computational cost).

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2024

Efficient distributed continual learning for steering experiments in real-time

Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training suffers from catastrophic forgetting (i.e., new patterns are reinforced at the expense of previously acquired knowledge). Training from scratch each time new training data becomes available would result in extremely long training times and massive data accumulation. Rehearsal-based continual learning has shown promise for addressing the catastrophic forgetting challenge, but research to date has not addressed performance and scalability. To fill this gap, we propose an approach based on a distributed rehearsal buffer that efficiently complements data-parallel training on multiple GPUs to achieve high accuracy, short runtime, and scalability. It leverages a set of buffers (local to each GPU) and uses several asynchronous techniques for updating these local buffers in an embarrassingly parallel fashion, all while handling the communication overheads necessary to augment input minibatches using unbiased, global sampling. We further propose a generalization of rehearsal buffers to support both classification and generative learning tasks, as well as more advanced rehearsal strategies (notably Dark Experience Replay, leveraging knowledge distillation). We illustrate this approach with a real-life HPC streaming application from the domain of ptychographic image reconstruction. Furthermore, we run extensive experiments on up to 128 GPUs of the ThetaGPU supercomputer to compare our approach with baselines representative of training-from-scratch (the upper bound in terms of accuracy) and incremental training (the lower bound). Results show that rehearsal-based continual learning achieves a top-5 validation accuracy close to the upper bound, while simultaneously exhibiting a runtime close to the lower bound.

Asynchronous data management↗
DOE OSTI2021

InversionNet3D: Efficient and Scalable Learning for 3-D Full-Waveform Inversion

Seismic full-waveform inversion (FWI) techniques aim to find a high-resolution subsurface geophysical model provided with waveform data. Some recent effort in data-driven FWI has shown some encouraging results in obtaining 2-D velocity maps. However, due to high computational complexity and large memory consumption, the reconstruction of 3-D high-resolution velocity maps via deep networks is still a great challenge. Here, in this article, we present InversionNet3D (InvNet3D), an efficient and scalable encoder–decoder network for 3-D FWI. The proposed method employs group convolution in the encoder to establish an effective hierarchy for learning information from multiple sources while cutting down unnecessary parameters and operations at the same time. The introduction of invertible layers further reduces the memory consumption of intermediate features during training and, thus, enables the development of deeper networks with more layers and higher capacity as required by different application scenarios. Experiments on the 3-D Kimberlina dataset demonstrate that InvNet3D achieves state-of-the-art reconstruction performance with lower computational cost and lower memory footprint compared to the baseline.

58 GEOSCIENCES↗
DOE OSTI2021

DeepMC: a deep learning method for efficient Monte Carlo beamlet dose calculation by predictive denoising in magnetic resonance-guided radiotherapy

Abstract Emerging magnetic resonance (MR) guided radiotherapy affords significantly improved anatomy visualization and, subsequently, more effective personalized treatment. The new therapy paradigm imposes significant demands on radiation dose calculation quality and speed, creating an unmet need for the acceleration of Monte Carlo (MC) dose calculation. Existing deep learning approaches to denoise the final plan MC dose fail to achieve the accuracy and speed requirements of large-scale beamlet dose calculation in the presence of a strong magnetic field for online adaptive radiotherapy planning. Our deep learning dose calculation method, DeepMC, addresses these needs by predicting low-noise dose from extremely noisy (but fast) MC-simulated dose and anatomical inputs, thus enabling significant acceleration. DeepMC simultaneously reduces MC sampling noise and predicts corrupted dose buildup at tissue-air material interfaces resulting from MR-field induced electron return effects. Here we demonstrate our model’s ability to accelerate dose calculation for daily treatment planning by a factor of 38 over traditional low-noise MC simulation with clinically meaningful accuracy in deliverable dose and treatment delivery parameters. As a post-processing approach, DeepMC provides compounded acceleration of large-scale dose calculation when used alongside established MC acceleration techniques in variance reduction and graphics processing unit-based MC simulation.

Engineering↗
DOE OSTI2025

Improving the efficiency of learning-based error mitigation

Error mitigation will play an important role in practical applications of near-term noisy quantum computers. Current error mitigation methods typically concentrate on correction quality at the expense of frugality (as measured by the number of additional calls to quantum hardware). To fill the need for highly accurate, yet inexpensive techniques, we introduce an error mitigation scheme that builds on Clifford data regression (CDR). The scheme improves the frugality by carefully choosing the training data and exploiting the symmetries of the problem. We test our approach by correcting long range correlators of the ground state of XY Hamiltonian on IBM Toronto quantum computer. We find that our method is an order of magnitude cheaper while maintaining the same accuracy as the original CDR approach. The efficiency gain enables us to obtain a factor of 10 improvement on the unmitigated results with the total budget as small as 2 ⋅ 10 5 shots. Furthermore, we demonstrate orders of magnitude improvements in frugality for mitigation of energy of the LiH ground state simulated with IBM's Ourense-derived noise model.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Decode the Workload: Training Deep Learning Models for Efficient Compute Cluster Representation

Monitoring the status of a high throughput computing cluster running computationally intensive production jobs is a crucial yet challenging system administration task due to the complexity of such systems. To this end, we train autoencoders using the Linux kernel CPU metrics of the cluster. Additionally, we explore assisting these models with graph neural networks to share information across threads within a compute node. The models are compared in terms of their ability to: 1) Produce a compressed latent representation that captures the salient features of the input, 2) Detect anomalous activity, and 3) Make distinction between different kinds of jobs run at Jefferson Lab. The goal is to have a robust encoder whose compressed embeddings are used for several downstream tasks. We extend this study further by deploying these models in a human-in-the-loop production-based setting for the anomaly detection task and discuss the associated implementation aspects such as continual learning and the criterion to generate alarms. This study represents a first step in the endeavor towards building self-supervised large-scale foundation models for computing centers.

Mohammed, Ahmed↗