Search NASA⌕ Search

SEARCH · Search NASA

Results for “continual learning”

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 OSTI2022

QuCNN : A Quantum Convolutional Neural Network with Entanglement Based Backpropagation

Quantum Machine Learning continues to be a highly active area of interest within Quantum Computing. Many of these approaches have adapted classical approaches to the quantum settings, such as QuantumFlow, etc. We push forward this trend, and demonstrate an adaption of the Classical Convolutional Neural Networks to quantum systems - namely QuCNN. QuCNN is a parameterised multi-quantum-state based neural network layer computing similarities between each quantum filter state and each quantum data state. With QuCNN, back propagation can be achieved through a single-ancilla qubit quantum routine. QuCNN is validated by applying a convolutional layer with a data state and a filter state over a small subset of MNIST images, comparing the backpropagated gradients, and training a filter state against an ideal target state.

high performance computing, quantum computing↗
DOE OSTI2018

Study of MHD Stability, Active Mode Control, and Disruption Avoidance in NSTX-U

Learning how to achieve sustained operation at high plasma pressure is an important goal of the National Spherical Torus Upgrade (NSTX-U) program and is critically important to any future fusion power plant. This research addresses high priority stability and control issues outlined by the NSTX-U Program. Reduced models of the stabilization physics learned continue to be created and tested against actual plasma operation in NSTX, NSTX-U, and other tokamak devices. This research is forming physics-based models for disruption forecasting that aims to unify results across different fusion machines for more confident extrapolation of the techniques studied to future devices including ITER. The Disruption Event Characterization and Forecasting (DECAF) code was expanded to analyze data from the TCV tokamak, including real-time MHD analysis signals. The presence of a mode and likelihood of its m/n numbers can be tracked, as well as the mode frequency, although a limitation at low frequency does not yet allow tracking modes to the locking point in TCV. Initial analyses of NSTX-U operation were conducted using the DECAF code. The timing of sawtooth oscillations was investigated taking advantage of the more extensive L-mode operation of the device in its first run campaign. An initial investigation of thermal collapses in NSTX-U was also conducted with specific comparison to the Greenwald density limit. A local island power balance model to explain the density limit in tokamaks has been tested with NSTX data and is being evaluated as a potential disruption forecaster in the DECAF code, presently showing similarities to the global Greenwald density evolution and limit. A module was written for the DECAF code that generalizes magnetic spectrogram analysis of MHD modes. This new portable code, written in Python, discriminates the toroidal mode number of instabilities and can track each mode as a DECAF event, monitoring the evolution of the mode through bifurcation and locking points. This is a critical new capability to allow disruption event characterization for general tokamak databases.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

PSIP For HDF5 Pilot Project (Final Report)

Productivity and Sustainability Improvement Planning (PSIP) is a lightweight, incremental and iterative approach (much in the same spirit as Agile methodologies) for making routine software process improvements in software projects. It is designed to be easily applied in existing development workflows. Quoting from a November 2019 workshop paper describing PSIP. PSIP breaks from classic software process improvement approaches such as CMM(I), SPICE, ISO 9000 or Six Sigma, in that it trades comprehensive standards and certification-driven assessment for self-defined, internally driven goals. It does, however, carry forward such ideas as having staged models of improvement (like CMM(I)) in the form of progress tracking cards. Additionally, PSIP is more aligned with lean and agile methods; it adopts their emphasis on iterative improvement and continuous learning. At its core, PSIP is an instantiation of the Plan-Do-Check-Act management cycle (PDCA, also known as Plan-Do-Study-Adjust) which provides the foundation for much of the modern software process improvement literature. This situates PSIP within a constellation of bottom-up, inductive software process improvement methods. PSIP is designed around the notion that already overburdened teams can define and carry out a series of small, incremental steps of progression towards improvement goals without significant (there will be some, but the goal is to avoid significant) disruption to ongoing development activities. A key enabling tool in PSIP is the use of Progress Tracking Cards (PTCs) which define the steps of progression towards a given improvement goal. This is the theory of PSIP. The PSIP for HDF5 project was aimed at putting PSIP into practice with the purpose of evaluating its effectiveness in planning and facilitating quality and process improvements in a scientific software project as well as its associated artifacts. The HDF5 project was chosen as a use case to evaluate PSIP for several reasons. First, NNSA labs and LLNL in particular have a keen interest in how HDF5 quality impacts its uptake and sustainability as a community adopted and supported code. Next, HDF5 is a foundational library, a key substrate in the HPC/CSE software stack, and any improvements there realized through this contract will have benefits to many DOE applications depending on it. HDF5 also represents an older, legacy code with technical debts to pay down. These characteristics are similar to many NNSA and even some ECP code projects. But, because HDF5 is an I/O library, it represents a simpler use case within which to study PSIP than a full-fledged and significantly more complex PDE simulation code. We believe these attributes make HDF5 an ideal use case for evaluating PSIP.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Visualization of the High-Burnup Spent Fuel Rod Phase 1 Test Plan: Technical Memo - Spent Fuel and Waste Disposition (Technical Memo)

Twenty-five high-burnup fuel rods were extracted from seven different fuel assemblies used for power production at the North Anna nuclear power plant and shipped to Oak Ridge National Laboratory (ORNL) in 2016 for detailed non-destructive examination (NDE) and destructive examination (DE). The spent fuel rods were from 17×17 lattices and consist of four cladding types—Zirlo ® , M5 ® , Zircaloy-4, and low tin Zircaloy-4 (Zirc-4). These spent fuel rods are being tested to provide: (a) baseline characterization and mechanical property data that can be used as a comparison to fuel that was loaded into a modified TN-32B cask in November 2017, as part of the high-burnup confirmatory data project and (b) data applicable to high-burnup fuel rods (>45 GWd/MTU) currently stored and to be stored in the dry-cask fleet. The TN-32B cask is referred to as the “Demo” cask and is currently expected to be transported to a separate location and the internal contents inspected in approximately ten years. ORNL has completed the NDE of the twenty-five fuel rods. The purpose of this technical memorandum is to present a simplified summary of the first phase of destructive examinations and test conditions that will be used for communicating with various stakeholders. The destructive examinations will leverage the expertise and capabilities from multiple national laboratories for performing independent measurements of relevant data. Close coordination is required to ensure that all examinations follow well documented procedures and are performed so that measured data and characteristics can be readily compared. Pacific Northwest National Laboratory (PNNL) has published a detailed overview of the test program. ORNL and PNNL developed detailed draft test plans for testing to be performed at their facilities. ORNL and PNNL are in the process of refining these test plans to apply specifically to the testing described in this memorandum. Argonne National Laboratory (ANL) contributed to the ORNL test plan by describing tests to be conducted at ANL. Testing will be based on continuous learning. If a test produces results that are inconsistent with expectations or current trends, further testing will be paused until a path forward is established to understand the results and to identify follow-on testing.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
NASA NTRS1990

System Identification for Nonlinear Control Using Neural Networks

An approach to incorporating artificial neural networks in nonlinear, adaptive control systems is described. The controller contains three principal elements: a nonlinear inverse dynamic control law whose coefficients depend on a comprehensive model of the plant, a neural network that models system dynamics, and a state estimator whose outputs drive the control law and train the neural network. Attention is focused on the system identification task, which combines an extended Kalman filter with generalized spline function approximation. Continual learning is possible during normal operation, without taking the system off line for specialized training. Nonlinear inverse dynamic control requires smooth derivatives as well as function estimates, imposing stringent goals on the approximating technique.

Stengel, Robert F.↗
NASA NTRS1992

A neural network prototyping package within IRAF

We outline our plans for incorporating a Neural Network Prototyping Package into the IRAF environment. The package we are developing will allow the user to choose between different types of networks and to specify the details of the particular architecture chosen. Neural networks consist of a highly interconnected set of simple processing units. The strengths of the connections between units are determined by weights which are adaptively set as the network 'learns'. In some cases, learning can be a separate phase of the user cycle of the network while in other cases the network learns continuously. Neural networks have been found to be very useful in pattern recognition and image processing applications. They can form very general 'decision boundaries' to differentiate between objects in pattern space and they can be used for associative recall of patterns based on partial cures and for adaptive filtering. We discuss the different architectures we plan to use and give examples of what they can do.

Bazell, D.↗
NASA NTRS2004

Graphical User Interface Development for Representing Air Flow Patterns

In the Turbine Branch, scientists carry out experimental and computational work to advance the efficiency and diminish the noise production of jet engine turbines. One way to do this is by decreasing the heat that the turbine blades receive. Most of the experimental work is carried out by taking a single turbine blade and analyzing the air flow patterns around it, because this data indicates the sections of the turbine blade that are getting too hot. Since the cost of doing turbine blade air flow experiments is very high, researchers try to do computational work that fits the experimental data. The goal of computational fluid dynamics is for scientists to find a numerical way to predict the complex flow patterns around different turbine blades without physically having to perform tests or costly experiments. When visualizing flow patterns, scientists need a way to represent the flow conditions around a turbine blade. A researcher will assign specific zones that surround the turbine blade. In a two-dimensional view, the zones are usually quadrilaterals. The next step is to assign boundary conditions which define how the flow enters or exits one side of a zone. way of setting up computational zones and grids, visualizing flow patterns, and storing all the flow conditions in a file on the computer for future computation. Such a program is necessary because the only method for creating flow pattern graphs is by hand, which is tedious and time-consuming. By using a computer program to create the zones and grids, the graph would be faster to make and easier to edit. Basically, the user would run a program that is an editable graph. The user could click and drag with the mouse to form various zones and grids, then edit the locations of these grids, add flow and boundary conditions, and finally save the graph for future use and analysis. My goal this summer is to create a graphical user interface (GUI) that incorporates all of these elements. I am writing the program in Java, a language that is portable among platforms, because it can run on different operating systems such as Windows and Unix without having to be rewritten. I had no prior experience of programming in Java at the start of my internship; I am continuously learning as I create the program. I have written the part of the program that enables a user to draw several zones, edit them, and store their locations. The next phase of my project is to allow the user to click on the side of a zone and create a boundary condition for it. A previous intern wrote a program that allows the user to input boundary conditions. I can integrate the two programs to create a larger, more usable program. After that, I will develop a way for the user to save the graph for future reference. Another eventual goal is to make the GUI capable of creating three-dimensional zones as well. Researchers such as my mentor, Dr. David Ashpis, need a quick, user-friendly

Chaudhary, Nilika↗
DOE OSTI2021

Luna

SAND2021-15051 O Luna is an experimental cognitive architecture that seeks to enable continuous learning in an embodied agent. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Dellana, Ryan↗
DOE OSTI2023

Reconstruction of decays to merged photons using end-to-end deep learning with domain continuation in the CMS detector

A novel technique based on machine learning is introduced to reconstruct the decays of highly Lorentz-boosted particles. Using an end-to-end deep learning strategy, the technique bypasses existing rule-based particle reconstruction methods typically used in high energy physics analyses. It uses minimally processed detector data as input and directly outputs particle properties of interest. The new technique is demonstrated for the reconstruction of the invariant mass of particles decaying in the CMS detector. The decay of a hypothetical scalar particle A into two photons, A → γ γ , is chosen as a benchmark decay. Lorentz boosts γ L = 60 – 600 are considered, ranging from regimes where both photons are resolved to those where the photons are closely merged as one object. A training method using domain continuation is introduced, enabling the invariant mass reconstruction of unresolved photon pairs in a novel way. The new technique is validated using π 0 → γ γ decays in LHC collision data.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS1991

Neuromorphic learning of continuous-valued mappings from noise-corrupted data

The effect of noise on the learning performance of the backpropagation algorithm is analyzed. A selective sampling of the training set is proposed to maximize the learning of control laws by backpropagation, when the data have been corrupted by noise. The training scheme is applied to the nonlinear control of a cart-pole system in the presence of noise. The neural computation provides the neurocontroller with good noise-filtering properties. In the presence of plant noise, the neurocontroller is found to be more stable than the teacher. A novel perspective on the application of neural network technology to control engineering is presented.

Troudet, T.↗
DOE OSTI2021

Universal Compiling and (No-)Free-Lunch Theorems for Continuous-Variable Quantum Learning

Quantum compiling, where a parameterized quantum circuit is trained to learn a target unitary, is an important primitive for quantum computing that can be used as a subroutine to obtain optimal circuits or as a tomographic tool to study the dynamics of an experimental system. While much attention has been paid to quantum compiling on discrete-variable hardware, less has been paid to compiling in the continuous-variable paradigm. Here we motivate several, closely related, short-depth continuous-variable algorithms for quantum compilation. We analyze the trainability of our proposed cost functions and numerically demonstrate our algorithms by learning arbitrary Gaussian operations and Kerr nonlinearities. We further make connections between this framework and quantum learning theory in the continuous-variable setting by deriving no-free-lunch theorems. These generalization bounds demonstrate a linear resource reduction for learning Gaussian unitaries using entangled coherent-Fock states and an exponential resource reduction for learning arbitrary unitaries using two-mode-squeezed states.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Anomaly Detection, Localization and Classification using Drifting Synchrophasor Data Streams

With ongoing automation and digitization of the electric power system, several Phasor Measurement Units(PMUs) have been deployed for monitoring and control. PMU data can have multiple anomalies, and many of the researchers in the past have concentrated on training machine/deep learning algorithms offline for anomaly detection over PMU data (i.e., not in real time). These machine/deep learning algorithms, when trained offline on a sample rather than a population of the dataset, fail to consider the dynamic behavior of the power grid in real-time, resulting in low accuracy. Considering the dynamic behavior of the power grid (e.g., change in load, generation, distributed energy resources (DERs) switching, network, controls), the definition of data anomalies varies in time and requires online training. A fundamental challenge is to enable online (i.e., real-time) training of machine/deep learning algorithms for anomaly detection over streaming PMU data. While machine/deep learning is often desirable to manage data streams, training a deep learning algorithm over streaming PMU data is nontrivial due to changes in data statistics caused by dynamic streaming data. This paper proposes PMUNET: a novel device-level deep learning-based data-driven approach for anomaly detection, localization, and classification over streaming PMU data, using online learning and multivariate data-drift detection algorithm .Two variants of PMUNET, Dynamic data Change Driven Learning (DCDL) and Continuity Driven Learning (CDL), are proposed and compared. DCDL aims to train the deep learning algorithm whenever the definition of anomaly changes due to the power grid dynamics. On the other hand, CDL continuously trains the deep learning algorithm over the PMU data-stream. The experimental results verify that DCDL outperforms CDL and other efficient anomaly detection methods over multiple events such as faults and load/ generator/capacitor/DERs variations/switching for IEEE 14 and 39 Bus test system as well as real PMU industrial data. The result verifies that DCDL variant of PMUNET improves over existing approach with a gain of 2% - 10% in terms of accuracy, false-positive rate, and false-negative rate.

adversarial deep learning↗
NASA NTRS1999

Cooperation and Coordination Between Fuzzy Reinforcement Learning Agents in Continuous State Partially Observable Markov Decision Processes

Successful operations of future multi-agent intelligent systems require efficient cooperation schemes between agents sharing learning experiences. We consider a pseudo-realistic world in which one or more opportunities appear and disappear in random locations. Agents use fuzzy reinforcement learning to learn which opportunities are most worthy of pursuing based on their promise rewards, expected lifetimes, path lengths and expected path costs. We show that this world is partially observable because the history of an agent influences the distribution of its future states. We consider a cooperation mechanism in which agents share experience by using and-updating one joint behavior policy. We also implement a coordination mechanism for allocating opportunities to different agents in the same world. Our results demonstrate that K cooperative agents each learning in a separate world over N time steps outperform K independent agents each learning in a separate world over K*N time steps, with this result becoming more pronounced as the degree of partial observability in the environment increases. We also show that cooperation between agents learning in the same world decreases performance with respect to independent agents. Since cooperation reduces diversity between agents, we conclude that diversity is a key parameter in the trade off between maximizing utility from cooperation when diversity is low and maximizing utility from competitive coordination when diversity is high.

Berenji, Hamid R.↗
DOE OSTI2026

Variational Optical Phase Learning on a Continuous-Variable Quantum Compiler

Quantum process learning is a fundamental primitive that draws inspiration from machine learning with the goal of better studying the dynamics of quantum systems. One approach to quantum process learning is quantum compilation, whereby an analog quantum operation is digitized by compiling it into a series of basic gates. While there has been significant focus on quantum compiling for discrete-variable systems, the continuous-variable (CV) framework has received comparatively less attention. We present an experimental implementation of a CV quantum compiler that uses two-mode squeezed light to learn a Gaussian unitary operation. We demonstrate the compiler by learning a parameterized linear phase unitary through the use of target and control phase unitaries to demonstrate a factor of 5.4 increase in the precision of the phase estimation and a 3.6-fold acceleration in the time-to-solution metric when leveraging quantum resources. We further show how our approach can be extended to higher-dimensional compilation tasks. Our results are enabled by the tunable control of our cost landscape via variable squeezing, thus providing a critical framework to simultaneously increase precision and reduce time-to-solution.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1993

Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning

Since most real-world applications of classification learning involve continuous-valued attributes, properly addressing the discretization process is an important problem. This paper addresses the use of the entropy minimization heuristic for discretizing the range of a continuous-valued attribute into multiple intervals.

discretization continuous-valued attributes classi↗
DOE OSTI2018

Eigenvector Continuation with Subspace Learning

A common challenge faced in quantum physics is finding the extremal eigenvalues and eigenvectors of a Hamiltonian matrix in a vector space so large that linear algebra operations on general vectors are not possible. There are numerous efficient methods developed for this task, but they generally fail when some control parameter in the Hamiltonian matrix exceeds some threshold value. In this Letter we present a new technique called eigenvector continuation that can extend the reach of these methods. The key insight is that while an eigenvector resides in a linear space with enormous dimensions, the eigenvector trajectory generated by smooth changes of the Hamiltonian matrix is well approximated by a very low-dimensional manifold. We prove this statement using analytic function theory and propose an algorithm to solve for the extremal eigenvectors. We benchmark the method using several examples from quantum many-body theory.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2024

Hamiltonian learning using machine-learning models trained with continuous measurements

Here, we build upon recent work on the use of machine-learning models to estimate Hamiltonian parameters using continuous weak measurement of qubits as input. We consider two settings for the training of our model: (1) supervised learning, where the weak-measurement training record can be labeled with known Hamiltonian parameters, and (2) unsupervised learning, where no labels are available. The first has the advantage of not requiring an explicit representation of the quantum state, thus potentially scaling very favorably to a larger number of qubits. The second requires the implementation of a physical model to map the Hamiltonian parameters to a measurement record, which we implement using an integrator of the physical model with a recurrent neural network to provide a model-free correction at every time step to account for small effects not captured by the physical model. We test our construction on a system of two qubits and demonstrate accurate prediction of multiple physical parameters in both the supervised context and the unsupervised context. We demonstrate that the model benefits from larger training sets, establishing that it is “learning,” and we show robustness regarding errors in the assumed physical model by achieving accurate parameter estimation in the presence of unanticipated single-particle relaxation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

Self-learning Monte Carlo method: Continuous-time algorithm

The recently introduced self-learning Monte Carlo method is a general-purpose numerical method that speeds up Monte Carlo simulations by training an effective model to propose uncorrelated configurations in the Markov chain. We implement this method in the framework of a continuous-time Monte Carlo method with an auxiliary field in quantum impurity models. We introduce and train a diagram generating function (DGF) to model the probability distribution of auxiliary field configurations in continuous imaginary time, at all orders of diagrammatic expansion. Furthermore, by using DGF to propose global moves in configuration space, we show that the self-learning continuous-time Monte Carlo method can significantly reduce the computational complexity of the simulation.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗