Search NASA⌕ Search

SEARCH · Search NASA

Results for “sequential training method”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

An adaptive Hessian approximated stochastic gradient MCMC method

Bayesian approaches have been successfully integrated into training deep neural networks. One popular family is stochastic gradient Markov chain Monte Carlo methods (SG-MCMC), which have gained increasing interest due to their ability to handle large datasets and the potential to avoid overfitting. Although standard SG-MCMC methods have shown great performance in a variety of problems, they may be inefficient when the random variables in the target posterior densities have scale differences or are highly correlated. Here, we present an adaptive Hessian approximated stochastic gradient MCMC method to incorporate local geometric information while sampling from the posterior. The idea is to apply stochastic approximation (SA) to sequentially update a preconditioning matrix at each iteration. The preconditioner possesses second-order information and can guide the random walk of a sampler efficiently. Instead of computing and saving the full Hessian of the log posterior, we use limited memory of the samples and their stochastic gradients to approximate the inverse Hessian-vector multiplication in the updating formula. Moreover, by smoothly optimizing the preconditioning matrix via SA, our proposed algorithm can asymptotically converge to the target distribution with a controllable bias under mild conditions. To reduce the training and testing computational burden, we adopt a magnitude-based weight pruning method to enforce the sparsity of the network. Our method is user-friendly and demonstrates better learning results compared to standard SG-MCMC updating rules. The approximation of inverse Hessian alleviates storage and computational complexities for large dimensional models. Numerical experiments are performed on several problems, including sampling from 2D correlated distribution, synthetic regression problems, and learning the numerical solutions of heterogeneous elliptic PDE. The numerical results demonstrate great improvement in both the convergence rate and accuracy.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1997

Design of Neural Networks for Fast Convergence and Accuracy: Dynamics and Control

A procedure for the design and training of artificial neural networks, used for rapid and efficient controls and dynamics design and analysis for flexible space systems, has been developed. Artificial neural networks are employed, such that once properly trained, they provide a means of evaluating the impact of design changes rapidly. Specifically, two-layer feedforward neural networks are designed to approximate the functional relationship between the component/spacecraft design changes and measures of its performance or nonlinear dynamics of the system/components. A training algorithm, based on statistical sampling theory, is presented, which guarantees that the trained networks provide a designer-specified degree of accuracy in mapping the functional relationship. Within each iteration of this statistical-based algorithm, a sequential design algorithm is used for the design and training of the feedforward network to provide rapid convergence to the network goals. Here, at each sequence a new network is trained to minimize the error of previous network. The proposed method should work for applications wherein an arbitrary large source of training data can be generated. Two numerical examples are performed on a spacecraft application in order to demonstrate the feasibility of the proposed approach.

Maghami, Peiman G.↗
DOE OSTI2020

Time Series Classification for Locating Forced Oscillation Sources

Here, this article presents a machine learning based time-series classification method for using synchrophasor measurements to locate the source of forced oscillation (FO) for fast disturbance removal. First, multivariate time series (MTS) matrices are constructed by the most informative measurements selected by sequential feature selection from each power plant. Then, the Mahalanobis matrix is trained such that the Mahalanobis distance between the MTSs from the same class (i.e., with the same FO source location) are minimized and from different classes (i.e., with different FO source locations) are maximized. This allows MTSs to be classified by classifiers with class membership corresponding to the location of each FO source. To meet the runtime requirements of online matching, class templates are constructed to reduce data size and improve matching efficiency. To account for uncertainty in identifying the exact beginning of an FO event, dynamic time warping is used to align the out-of-sync MTSs. IEEE 39bus and WECC 179bus systems are used for algorithm development and validation. Simulation results demonstrate that the algorithm meets online operation runtime requirement with high accuracy using misaligned data sets.

42 ENGINEERING↗
NASA NTRS1999

Context-Specific Adaptation of Gravity-Dependent Vestibular Reflex Responses (NSBRI Neurovestibular Project 1)

Impairment of gaze and head stabilization reflexes can lead to disorientation and reduced performance in sensorimotor tasks such as piloting of spacecraft. Transitions between different gravitoinertial force (gif) environments - as during different phases of space flight - provide an extreme test of the adaptive capabilities of these mechanisms. We wish to determine to what extent the sensorimotor skills acquired in one gravity environment will transfer to others, and to what extent gravity serves as a context cue for inhibiting such transfer. We use the general approach of adapting a response (saccades, vestibuloocular reflex: VOR, or vestibulocollic reflex: VCR) to a particular change in gain or phase in one gif condition, adapting to a different gain or phase in a second gif condition, and then seeing if gif itself - the context cue - can recall the previously-learned adapted responses. Previous evidence indicates that unless there is specific training to induce context-specificity, reflex adaptation is sequential rather than simultaneous. Various experiments in this project investigate the behavioral properties, neurophysiological basis, and anatomical substrate of context-specific learning, using otolith (gravity) signals as a context cue. In the following, we outline the methods for all experiments in this project, and provide details and results on selected experiments.

Shelhamer, Mark↗
DOE OSTI2025

Enhancing Unknown Waveform Detection by Learning Intra and Inter-domain Dependencies with Advanced Attention Fusion Mechanisms

Detection of unknown waveforms in mission-critical communications is a crucial area of interest for the Department of Energy (DoE). Traditional methods and recent deep learning-based approaches often assume that the training set includes all possible classes, which is impractical for detecting new waveforms. This limitation gives rise to the problem of open-set recognition (OSR), which involves correctly identifying known classes while detecting and rejecting unknown or unseen classes. To address this limitation, we propose a novel dual-domain complex-valued neural architecture that jointly processes time-domain and frequency-domain signal representations using transformer mechanisms. A transformer model is a deep learning architecture that uses self-attention mechanisms to process and learn relationships in sequential data. Our model employs a cosine similarity loss to extract domain-specific features and incorporates a transformer architecture in the latent space to weigh the importance of different features from the time and frequency domains. The transformer layer includes stacked self-attention and cross-attention modules to learn intra-domain and inter-domain dependencies, creating a more holistic signal representation. An attention-based fusion module intelligently combines the time and frequency-domain features using multi-head attention, enabling the network to learn the optimal feature for each domain in each input signal. Quantitative results demonstrate the impact of these architectural choices on overall performance, showing significant improvement after incorporating self and cross-attention modules and using complex attention fusion over simple weighted fusion. Our ongoing work will focus on addressing the limitations of threshold-based OSR methods by developing a novel generative framework that integrates a conditional diffusion probabilistic model (DPM). DPM is a generative framework that learns to synthesize complex data by reversing a gradual noising process using a neural network trained to denoise step-by-step. Our goal is to leverage the inherent strengths of DPMs for identifying unknown signals more robustly. One primary advantage of using a DPM is its ability to provide a more reliable anomaly score based on the model's reconstruction error, rather than relying solely on classifier confidence. Additionally, the iterative denoising process of DPMs makes this approach naturally resilient to low Signal-to-Noise Ratio (SNR) conditions, where traditional methods often fail. By implementing this generative framework, we aim to enhance the model's capability to accurately detect unknown waveforms and maintain performance in challenging environments.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2021

Experimentally Driven Automated Machine-Learned Interatomic Potential for a Refractory Oxide

Understanding the structure and properties of refractory oxides is critical for high temperature applications. In this work, a combined experimental and simulation approach uses an automated closed loop via an active learner, which is initialized by x-ray and neutron diffraction measurements, and sequentially improves a machine-learning model until the experimentally predetermined phase space is covered. Furthermore, a multiphase potential is generated for a canonical example of the archetypal refractory oxide, HfO 2 , by drawing a minimum number of training configurations from room temperature to the liquid state at similar to 2900 degrees C. The method significantly reduces model development time and human effort.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2022

Scalable Second Order Optimization for Machine Learning

Many machine learning (ML) training tasks are essentially optimization processes that would at first glance appear eminently parallelizable and scalable. However, effective acceleration of these tasks with scalable parallel hardware has proven to be elusive. While standard methods for machine learning, e.g., stochastic gradient descent (SGD) for DNNs, tend to be resource efficient, they appear to be fundamentally sequential in nature.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Sequence-Based Anomaly Detection in Critical Infrastructure Networks

United States critical infrastructure faces new cyber threats from adversarial nation-state actors in the form of malware-free attacks. Traditional cybersecurity techniques use rules-based methods to identify indicators of compromise on networks, often missing these sophisticated attacks. Our approach leverages multiple state of the art machine learning models in a pipeline to identify abnormal network events through sequential analysis. We combine both device and packet-level information into individual events to characterize anomalous network actions. The model is trained and tested on real network traffic from the Idaho National Lab High Performance Computing (HPC) with greater than 98% precision. It is capable of flagging malicious tactics used by adversaries in malware-free attacks, severe changes to the network, and abnormal user activity by network devices.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

Quantifying neptunium oxidation states in nitric acid through spectroelectrochemistry and chemometrics

Controlled-potential in situ thin-layer spectropotentiometry was leveraged to generate visible/near-infrared (VIS/NIR) absorption spectral data sets for the development of chemometric models to quantify Np(III/IV/V/VI) oxidation states in HNO 3 . This technology would be valuable in laboratory studies and when monitoring process solutions to guide feed adjustments for radiochemical separations—the performance of which depends on oxidation state. This approach successfully isolated and stabilized Np species in pure (~99%) oxidation states without compromising solution optical properties. Multivariate curve resolution–alternating least squares models were evaluated to resolve spectral and component concentrations from a scan that sequentially produced Np(VI), Np(V), Np(IV), and Np(III) spectra with mixtures of two valences at a time. Although it provided a useful approximation, the method was not able to quantitively resolve each component likely because of rotational ambiguity. Additionally, partial least squares regression models were built from artificial and electrochemically generated VIS/NIR spectral training sets to study the effect of interionic interactions on spectral characteristics. Models built with true Bi-chemical mixtures of coexisting Np oxidation states and spectra generated from additive combinations of pure end points had similar prediction performance. This methodology can be used to directly quantify Np concentration and the ratio of Np oxidation states and other actinides in remote settings such as hot cells.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗
DOE OSTI2020

Quantum adiabatic machine learning by zooming into a region of the energy surface

Recent work has shown that quantum annealing for machine learning, referred to as QAML, can perform comparably to state-of-the-art machine learning methods with a specific application to Higgs boson classification. Here, we propose QAML-Z, an algorithm that iteratively zooms in on a region of the energy surface by mapping the problem to a continuous space and sequentially applying quantum annealing to an augmented set of weak classifiers. Results on a programmable quantum annealer show that QAML-Z matches classical deep neural network performance at small training set sizes and reduces the performance margin between QAML and classical deep neural networks by almost 50% at large training set sizes, as measured by area under the receiver operating characteristic curve. The significant improvement of quantum annealing algorithms for machine learning and the use of a discrete quantum algorithm on a continuous optimization problem both opens a class of problems that can be solved by quantum annealers and suggests the approach in performance of near-term quantum machine learning towards classical benchmarks.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

A Hybrid Reinforcement Learning-MPC Approach for Distribution System Critical Load Restoration: Preprint

This paper proposes a hybrid control approach for distribution system critical load restoration, combining deep reinforcement learning (RL) and model predictive control (MPC) aiming at maximizing total restored load following an extreme event. RL determines a policy for quantifying operating reserve requirements, thereby hedging against uncertainty, while MPC models grid operations incorporating RL policy actions, i.e., the reserve requirement, renewable (wind and solar) power predictions, and load demand forecasts. We formulate the reserve requirement determination problem as a sequential decision making problem based on the Markov Decision Process (MDP) and design an RL learning environment based on the OpenAI Gym framework and MPC. The RL agent reward and MPC objective function aim to maximize and monotonically increase total restored load and minimize load shedding and renewable power curtailment. The RL algorithm is trained off-line using historical forecast of renewable generation and load demand. The method is tested using a modified IEEE 13-bus distribution test feeder containing wind turbine, photovoltaic, microturbine and battery. Case studies demonstrated that the proposed method outperforms other operating reserve determination methods.

distribution system↗
DOE OSTI2022

A Hybrid Reinforcement Learning-MPC Approach for Distribution System Critical Load Restoration

This paper proposes a hybrid control approach for distribution system critical load restoration, combining deep reinforcement learning (RL) and model predictive control (MPC) aiming at maximizing total restored load following an extreme event. RL determines a policy for quantifying operating reserve requirements, thereby hedging against uncertainty, while MPC models grid operations incorporating RL policy actions (i.e., reserve requirements), renewable (wind and solar) power predictions, and load demand forecasts. We formulate the reserve requirement determination problem as a sequential decision-making problem based on the Markov Decision Process (MDP) and design an RL learning environment based on the OpenAI Gym framework and MPC simulation. The RL agent reward and MPC objective function aim to maximize and monotonically increase total restored load and minimize load shedding and renewable power curtailment. The RL algorithm is trained offline using a historical forecast of renewable generation and load demand. The method is tested using a modified IEEE 13-bus distribution test feeder containing wind turbine, photovoltaic, microturbine, and battery. Case studies demonstrated that the proposed method outperforms other policies with static operating reserves.

distribution system↗
NASA NTRS2026

Incremental Learning for Passive Microwave Precipitation Retrievals using Advanced Technology Microwave Sounder

Spaceborne passive microwave (PMW) radiometry is central to global precipitation monitoring, yet retrieval uncertainties remain substantial, particularly for cross-track sounders whose variable footprints and channel configurations are optimized for atmospheric temperature and moisture profiling rather than precipitation. Consequently, existing operational products often exhibit angular-dependent biases, limited effective swath utilization, unrealistic rainfall probability distributions, and systematic misclassification of precipitation phase. These limitations are further compounded by the scarcity of globally accurate and representative precipitation observations, as training data from the Dual-frequency Precipitation Radar (DPR) and the Cloud Profiling Radar (CPR) are spatially sparse, lack uniform global coverage, and exhibit heterogeneous error characteristics across precipitation regimes. To address these challenges, this study presents a supervised retrieval algorithm that incrementally trains an ensemble of extreme gradient-boosted decision trees by augmenting base learners with pre-training on reanalysis data and post-training on coincident DPR and CPR observations matched with the Advanced Technology Microwave Sounder (ATMS). By transferring prior information from reanalysis to posterior constraints from radar observations and adopting a sequential detection–estimation strategy for precipitation phase and rate retrieval, the proposed approach yields retrievals across the full ATMS swath that are largely free from persistent deficiencies in current Global Precipitation Measurement (GPM) passive microwave operational products. In particular, the method resolves bimodal artifacts in rainfall retrievals and mitigates systematic high-latitude snowfall biases, including overestimation across the Arctic and underestimation across the Antarctic. Validation against independent Multi-Radar Multi-Sensor (MRMS) data over the Contiguous United States (CONUS) further demonstrates improved performance in precipitation phase detection and rate estimation relative to both reanalysis and current GPM PMW products.

Mahyar Garshasbi↗
DOE OSTI2021

Gaming the beamlines—employing reinforcement learning to maximize scientific outcomes at large-scale user facilities

Abstract Beamline experiments at central facilities are increasingly demanding of remote, high-throughput, and adaptive operation conditions. To accommodate such needs, new approaches must be developed that enable on-the-fly decision making for data intensive challenges. Reinforcement learning (RL) is a domain of AI that holds the potential to enable autonomous operations in a feedback loop between beamline experiments and trained agents. Here, we outline the advanced data acquisition and control software of the Bluesky suite, and demonstrate its functionality with a canonical RL problem: cartpole. We then extend these methods to efficient use of beamline resources by using RL to develop an optimal measurement strategy for samples with different scattering characteristics. The RL agents converge on the empirically optimal policy when under-constrained with time. When resource limited, the agents outperform a naive or sequential measurement strategy, often by a factor of 100%. We interface these methods directly with the data storage and provenance technologies at the National Synchrotron Light Source II, thus demonstrating the potential for RL to increase the scientific output of beamlines, and layout the framework for how to achieve this impact.

36 MATERIALS SCIENCE↗
DOE OSTI2023

CCSI Toolset 3.19 Release

CCSI Toolset 3.19 Release Highlights A gradient generation tool was developed to support GENN models in FOQUS. Certain machine learning tools train gradient-enhanced neural network (GENN) models which can be more accurate for complex datasets given a priori knowledge of model derivatives. However, the derivatives must be known beforehand and are not often available for process data. This tool automatically predicts the gradients for a training dataset in a form usable by common GENN trainers, such as Surrogate Modeling Toolbox. Support was added for Surrogate Modeling Toolbox GENN models in FOQUS, including updates to the run methods, node properties, test framework, documentation and optional dependencies list. Users can train/save Surrogate Modeling Toolbox gradient-enhanced neural network (GENN) models with custom objects and produce .pkl files compatible with the Machine Learning/Artificial Intelligence Plugin in FOQUS. A simpler implementation of the ordering algorithm in the Sequential Design of Experiments (SDOE) module was included. The SDOE examples documentation was updated. The Optimality-Based Design of Experiments was updated to improve the error handling when the results are None.

AS↗
DOE OSTI2023

Safe Exploration Reinforcement Learning for Load Restoration using Invalid Action Masking

This paper addresses the load restoration problem after a power outage event. Our primary proposed methodology uses a multi-agent reinforcement learning method to make the optimal sequential decisions on picking up critical loads. Typically, a negative reward is provided to discourage the agents from selecting decisions that violate physical constraints during the restoration process. However, the main disadvantage of this approach is its difficulty in applying it to large-scale systems due to the curse of dimensionality. This paper introduces the invalid action masking technique to overcome this limitation. The features of this technique include zero physical constraint violations, reduced training time, and stabilization of the explo- ration process. Simulation results are performed in IEEE 13-node and IEEE 123-node systems showing the better performance of the proposed algorithm in comparison to the conventional approaches both in terms of restored power and learning curve.

reinforcement learning, blackstart, artificial int↗
DOE OSTI2025

Direct nonparametric multimessenger constraints on the equation of state of cold dense nuclear matter

We utilize the now substantial amount of astrophysical observations of neutron stars (NSs), along with perturbative quantum chromodynamics (pQCD) calculations at high density, to directly constrain the NS equation of state (EOS). To this end, we construct nonparametric EOS priors by using Gaussian processes trained on 75 EOSs, which include models with either hadrons, hyperons, or quarks at high densities. We create a prior using the full EOS sample (model agnostic), and one prior for each EOS family to test model discrimination. We introduce a novel inference approach, which allows the simultaneous sampling of intrinsic and extrinsic parameters of binary NS mergers, as well as a nonparametric equation of state. We showcase this method in a Bayesian updating scheme by first performing a complete analysis of the binary NS merger event GW170817 with minimal assumptions, and sequentially adding information from x-ray and radio NS observations, along with pQCD calculations. Besides providing standard constraints, such as the pressure at twice nuclear saturation density 𝑝⁡(2⁢𝜌 sat ) = 4.3$^{+0.6}_{−0.6}$ × 10 34 dyne/cm 2 , at 95% confidence level, for the model agnostic prior, our methodology shows how the choice of EOS families used in conditioning changes the inferred astrophysical properties of the EOS, namely tidal deformability and maximum supported NS mass. We find hyperonic priors predicting higher tidal deformabilities for a 1.4⁢𝑀 ⊙ NS, and hadronic priors being preferred by the considered astrophysical data.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Heterogeneous Graph Neural Network for identifying hadronically decayed tau leptons at the High Luminosity LHC

Here, we present a new algorithm that identifies reconstructed jets originating from hadronic decays of tau leptons against those from quarks or gluons. No tau lepton reconstruction algorithm is used. Instead, the algorithm represents jets as heterogeneous graphs with tracks and energy clusters as nodes and trains a Graph Neural Network to identify tau jets from other jets. Different attributed graph representations and different GNN architectures are explored. We propose to use differential track and energy cluster information as node features and a heterogeneous sequentially-biased encoding for the inputs to final graph-level classification.

47 OTHER INSTRUMENTATION↗