Search NASA⌕ Search

SEARCH · Search NASA

Results for “adaptive 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 955 records · Page 53

A multi-backend autotuning study of feature selection on GPUs

Abstract Feature selection is an important step in machine learning that can benefit from GPU acceleration. As the number of GPU vendors increases, it is imperative to adapt algorithms such as the minimum Redundancy Maximum Relevance (mRMR) feature selection method to different backends that support several GPU architectures. This work presents a multi-backend implementation of mRMR across CUDA, HIP, and SYCL, and studies its performance when combined with Bayesian optimization and transfer learning to automatically tune execution parameters for different platforms and datasets. Our experimental results show that when tuned, CUDA and HIP achieve comparable performance on NVIDIA architectures, while SYCL exhibits a moderate performance gap. Overall, this work highlights the impact of backend choice and autotuning on GPU-accelerated feature selection and provides insights into deploying mRMR across heterogeneous environments.

Beceiro, Bieito (ORCID:0000000333014890)↗

A Study on Efficient Reinforcement Learning Through Knowledge Transfer

Although Reinforcement Learning (RL) algorithms have made impressive progress in learning complex tasks over the past years, there are still prevailing short-comings and challenges. Specifically, the sample-inefficiency and limited adaptation across tasks often make classic RL techniques impractical for real-world applications despite the gained representational power when combining deep neural networks with RL, known as Deep Reinforcement Learning (DRL). Recently, a number of approaches to address those issues have emerged. Many of those solutions are based on smart DRL architectures that enhance single task algorithms with the capability to share knowledge between agents and across tasks by introducing Transfer Learning (TL) capabilities. Here this survey addresses strategies of knowledge transfer from simple parameter sharing to privacy preserving federated learning and aims at providing a general overview of the field of TL in the DRL domain, establishes a classification framework, and briefly describes representative works in the area.

97 MATHEMATICS AND COMPUTING↗

Few-Shot Learning Enables Population-Scale Analysis of Leaf Traits in Populus trichocarpa

Plant phenotyping is typically a time-consuming and expensive endeavor, requiring large groups of researchers to meticulously measure biologically relevant plant traits, and is the main bottleneck in understanding plant adaptation and the genetic architecture underlying complex traits at population scale. In this work, we address these challenges by leveraging few-shot learning with convolutional neural networks to segment the leaf body and visible venation of 2,906 Populus trichocarpa leaf images obtained in the field. In contrast to previous methods, our approach (a) does not require experimental or image preprocessing, (b) uses the raw RGB images at full resolution, and (c) requires very few samples for training (e.g., just 8 images for vein segmentation). Traits relating to leaf morphology and vein topology are extracted from the resulting segmentations using traditional open-source image-processing tools, validated using real-world physical measurements, and used to conduct a genome-wide association study to identify genes controlling the traits. In this way, the current work is designed to provide the plant phenotyping community with (a) methods for fast and accurate image-based feature extraction that require minimal training data and (b) a new population-scale dataset, including 68 different leaf phenotypes, for domain scientists and machine learning researchers. All of the few-shot learning code, data, and results are made publicly available.

59 BASIC BIOLOGICAL SCIENCES↗

Understanding the Physics Representation of Deep Learning Models in Environmental Applications

Deep learning (DL) models have been popular in earth and environmental modeling and analysis, which exhibit huge potential in capturing and reconstructing the non-linearity of relevant environmental processes. They are extensively used as analytical tools or emulators for multiple domains (atmosphere, land surface, ocean, and biogeochemistry). Despite their success, their internal working mechanism remains largely unknown. Such a lack of knowledge hinders the identification of physically consistent models that are fully adaptive to non-stationary climate, as well as the development of physics-informed machine learning such as physics-informed neural network (PINN). To establish preliminary knowledge and framework of such physics representation evaluation, this project focuses on an improved understanding of DL models in the environmental applications. DL models are increasingly applied to environmental modeling and prediction. However, they have been evaluated mostly from a performance perspective, and there is a gap in understanding how they represent the known physics internally. Such knowledge is especially critical when applying DL models under climate change conditions, where new inputs are likely outside the ranges of the training datasets. In this project, we reveal how the known physical processes are represented within DL models from both statistical and mechanistic perspectives. Leveraging the traditional model evaluations that focus more on the accuracies of predictions, we establish a framework that examines both the accuracy and physics representation of DL models. This analysis framework can identify DL models that make the correct predictions based on correct physics, thus enhancing the existing explainable artificial intelligence (explainable-AI) portfolio. It lays a foundation for developing novel metrics to evaluate the emerging DL models in environmental applications. This knowledge also informs the development of physics-informed DL models by revealing the direct connections between the known physical processes and specific model components or structures.

54 ENVIRONMENTAL SCIENCES↗

An Ensemble Approach to Building Mercer Kernels with Prior Information

This paper presents a new methodology for automatic knowledge driven data mining based on the theory of Mercer Kernels, which are highly nonlinear symmetric positive definite mappings from the original image space to a very high, possibly dimensional feature space. we describe a new method called Mixture Density Mercer Kernels to learn kernel function directly from data, rather than using pre-defined kernels. These data adaptive kernels can encode prior knowledge in the kernel using a Bayesian formulation, thus allowing for physical information to be encoded in the model. Specifically, we demonstrate the use of the algorithm in situations with extremely small samples of data. We compare the results with existing algorithms on data from the Sloan Digital Sky Survey (SDSS) and demonstrate the method's superior performance against standard methods. The code for these experiments has been generated with the AUTOBAYES tool, which automatically generates efficient and documented C/C++ code from abstract statistical model specifications. The core of the system is a schema library which contains templates for learning and knowledge discovery algorithms like different versions of EM, or numeric optimization methods like conjugate gradient methods. The template instantiation is supported by symbolic-algebraic computations, which allows AUTOBAYES to find closed-form solutions and, where possible, to integrate them into the code.

Srivastava, Ashok N.↗

Featureless adaptive optimization accelerates functional electronic materials design

Electronic materials that exhibit phase transitions between metastable states (e.g., metal-insulator transition materials with abrupt electrical resistivity transformations) are challenging to decode. For these materials, conventional machine learning methods display limited predictive capability due to data scarcity and the absence of features that impede model training. In this article, we demonstrate a discovery strategy based on multi-objective Bayesian optimization to directly circumvent these bottlenecks by utilizing latent variable Gaussian processes combined with high-fidelity electronic structure calculations for validation in the chalcogenide lacunar spinel family. We directly and simultaneously learn phase stability and bandgap tunability from chemical composition alone to efficiently discover all superior compositions on the design Pareto front. Previously unidentified electronic transitions also emerge from our featureless adaptive optimization engine. Our methodology readily generalizes to optimization of multiple properties, enabling co-design of complex multifunctional materials, especially where prior data is sparse.

36 MATERIALS SCIENCE↗

Machine learning control of an elliptically bent hard x-ray mirror

This article showcases the high-resolution control of an elliptically bent hard X-ray mirror optics at the Advanced Photon Source. The mirror uses a compact laminar flexure bending mechanism to achieve elliptical shapes covering a large range of focal distances. An array of capacitive sensors are used as a surface profiler for in-situ monitoring of the mirror shape. Machine learning and control techniques were used to change the mirror shape and focus the incident X-ray at predefined focal planes. The mirror surface shape error can be controlled to be within 40 nm rms with high repeatability. This technique gives the capability to focus incident X-ray beam within a range of focal distances corresponding to shape deformation range of a mirror optics. This work would be beneficial for controlling similar adaptive optics for multiple adaptive optics systems.

adaptive optics↗

BioSentinel: Mission Summary and Lessons Learned From the First Deep Space Biology CubeSat Mission

Launched on Artemis-1, BioSentinel carries a biology experiment into deep space for the first time in 50 years. A 6U CubeSat form factor was utilized for the spacecraft which included technologies newly developed or adapted for operations beyond Earth orbit. The spacecraft carries onboard budding yeast, Saccharomyces cerevisiae, as an analog to human cells to test the biological response to deep space radiation. This was the maiden deep-space voyage for many of the subsystems, and the first time to evaluate their performance in flight operation. Flying a CubeSat beyond LEO comes with unique challenges with respect to trajectory uncertainty and mission operations planning. The nominal plan was a lunar fly-by, followed by an insertion into Heliocentric orbit. However, some possible scenarios included lunar eclipses that could have severely impacted the power budget during that phase of the mission, while others could have resulted in a “Retrograde” hyperbola at swing-by resulting in the spacecraft traveling inward toward Earth or even towards a collision with the lunar surface. The commissioning phase of the mission was successful and completed a week ahead of schedule. It did not come without its exciting moments and challenges. First contact with the spacecraft uncovered that the vehicle was unexpectedly tumbling after deployment, a situation that needed to be corrected urgently. The mission operations team executed a contingency plan to stabilize the spacecraft, with just moments to spare before the battery ran out of power. The BioSensor payload onboard the spacecraft is a complex instrument that includes microfluidics, fluid systems, sensor control electronics, as well at the living yeast cells. BioSentinel also included a TimePix radiation sensor implemented by JSC’s RadWorks group. Dose and Linear Energy Transfer (LET) data is compared directly to the rate of DSB-and repair events measured by the S. cerevisiae cells. BioSentinel mature nanosatellite technologies included: deep space communications and navigation, autonomous attitude control and momentum management, and micro-propulsion systems, to provide an adaptable nanosatellite platform for deep space uses. This paper discusses the performance of the BioSentinel spacecraft through the mission phase, and includes lessons learned from challenges and anomalies. BioSentinel had many successes and will be a pathfinder for future deep space CubeSats and biology missions.

BioSentinel↗

Biosentinel: Mission Summary and Lessons Learned From the First Deep Space Biology CubeSat Mission

Launched on Artemis-1, BioSentinel carries a biology experiment into deep space for the first time in 50 years. A 6U CubeSat form factor was utilized for the spacecraft which included technologies newly developed or adapted for operations beyond Earth orbit. The spacecraft carries onboard budding yeast, Saccharomyces cerevisiae, as an analog to human cells to test the biological response to deep space radiation. This was the maiden deep-space voyage for many of the subsystems, and the first time to evaluate their performance in flight operation. Flying a CubeSat beyond LEO comes with unique challenges with respect to trajectory uncertainty and mission operations planning. The nominal plan was a lunar fly-by, followed by an insertion into Heliocentric orbit. However, some possible scenarios included lunar eclipses that could have severely impacted the power budget during that phase of the mission, while others could have resulted in a “Retrograde” hyperbola at swing-by resulting in the spacecraft traveling inward toward Earth or even towards a collision with the lunar surface. The commissioning phase of the mission was successful and completed a week ahead of schedule. It did not come without its exciting moments and challenges. First contact with the spacecraft uncovered that the vehicle was unexpectedly tumbling after deployment, a situation that needed to be corrected urgently. The mission operations team executed a contingency plan to stabilize the spacecraft, with just moments to spare before the battery ran out of power. The BioSensor payload onboard the spacecraft is a complex instrument that includes microfluidics, fluid systems, sensor control electronics, as well at the living yeast cells. BioSentinel also included a TimePix radiation sensor implemented by JSC’s RadWorks group. Dose and Linear Energy Transfer (LET) data is compared directly to the rate of DSB-and repair events measured by the S. cerevisiae cells. BioSentinel mature nanosatellite technologies included: deep space communications and navigation, autonomous attitude control and momentum management, and micro-propulsion systems, to provide an adaptable nanosatellite platform for deep space uses. This paper discusses the performance of the BioSentinel spacecraft through the mission phase, and includes lessons learned from challenges and anomalies. BioSentinel had many successes and will be a pathfinder for future deep space CubeSats and biology missions.

BioSentinel↗

A Modular and Transferable Reinforcement Learning Framework for the Fleet Rebalancing Problem

Mobility on demand (MoD) systems show great promise in realizing flexible and efficient urban transportation. However, significant technical challenges arise from operational decision making associated with MoD vehicle dispatch and fleet rebalancing. For this reason, operators tend to employ simplified algorithms that have been demonstrated to work well in a particular setting. To help bridge the gap between novel and existing methods, we propose a modular framework for fleet rebalancing based on model-free reinforcement learning (RL) that can leverage an existing dispatch method to minimize system cost. In particular, by treating dispatch as part of the environment dynamics, a centralized agent can learn to intermittently direct the dispatcher to reposition free vehicles and mitigate against fleet imbalance. We formulate RL state and action spaces as distributions over a grid partitioning of the operating area, making the framework scalable and avoiding the complexities associated with multiagent RL. Numerical experiments, using real-world trip and network data, demonstrate that RL reduces waiting time by 28% to 38% for the same-day evaluation, 17% to 44% for cross-day evaluation, and 22% to 25% for cross-season evaluation compared with no rebalancing scenarios. This approach has several distinct advantages over baseline methods including: improved system cost; high degree of adaptability to the selected dispatch method; and the ability to perform scale-invariant transfer learning between problem instances with similar vehicle and request distributions.

33 ADVANCED PROPULSION SYSTEMS↗

NASA Tech Briefs, July 2010

Topics covered include: Wirelessly Interrogated Wear or Temperature Sensors; Processing Nanostructured Sensors Using Microfabrication Techniques; Optical Pointing Sensor; Radio-Frequency Tank Eigenmode Sensor for Propellant Quantity Gauging; High-Temperature Optical Sensor; Integral Battery Power Limiting Circuit for Intrinsically Safe Applications; Configurable Multi-Purpose Processor; Squeezing Alters Frequency Tuning of WGM Optical Resonator; Automated Computer Access Request System; Range Safety for an Autonomous Flight Safety System; Fast and Easy Searching of Files in Unisys 2200 Computers; Parachute Drag Model; Evolutionary Scheduler for the Deep Space Network; Modular Habitats Comprising Rigid and Inflatable Modules; More About N2O-Based Propulsion and Breathable-Gas Systems; Ultrasonic/Sonic Rotary-Hammer Drills; Miniature Piezoelectric Shaker for Distribution of Unconsolidated Samples to Instrument Cells; Lunar Soil Particle Separator; Advanced Aerobots for Scientific Exploration; Miniature Bioreactor System for Long-Term Cell Culture; Electrochemical Detection of Multiple Bioprocess Analytes; Fabrication and Modification of Nanoporous Silicon Particles; High-Altitude Hydration System; Photon Counting Using Edge-Detection Algorithm; Holographic Vortex Coronagraph; Optical Structural Health Monitoring Device; Fuel-Cell Power Source Based on Onboard Rocket Propellants; Polar Lunar Regions: Exploiting Natural and Augmented Thermal Environments; Simultaneous Spectral Temporal Adaptive Raman Spectrometer - SSTARS; Improved Speed and Functionality of a 580-GHz Imaging Radar; Bolometric Device Based on Fluxoid Quantization; Algorithms for Learning Preferences for Sets of Objects; Model for Simulating a Spiral Software-Development Process; Algorithm That Synthesizes Other Algorithms for Hashing; Algorithms for High-Speed Noninvasive Eye-Tracking System; and Adapting ASPEN for Orbital Express.

Source record↗

Methods for evaluation and treatment of data shift

This is a code repository for a set of tools for detecting and mitigating data shifts in machine learning. The goal of the tools is to provide capabilities for determining when new data sets differ from training data sets and for adapting existing models to new data or correcting data shifts (via domain adaptation). The components will be written in Python, a high-level programming language that takes advantage of the Python ecosystem of high-quality open-source packages for machine learning and signal processing.

Parikh, Nidhi↗

Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models

This study aims to implement a hybrid ensemble surrogate machine learning technique in predicting the compressive strength (CS) of concrete, an important parameter used for durability design and service life prediction of concrete structures in civil engineering projects. For this purpose, an experimental database consisting of 1030 records has been compiled from the machine learning repository of the University of California, Irvine. The database was used to train and validate four conventional machine learning (CML) models, namely Artificial Neural Network (ANN), Linear and Non-Linear Multivariate Adaptive Regression Splines (MARS-L and MARS-C), Gaussian Process Regression (GPR), and Minimax Probability Machine Regression (MPMR). Subsequently, the predicted outputs of CML models were combined and trained using ANN to construct the Hybrid Ensemble Model (HENSM). It is observed that the proposed HENSM produces higher predictive accuracy compared to the CML models used in the present study. The predictive performance of all models for CS prediction was compared using the testing dataset and it is found that the HENSM model attained the highest predictive accuracy in both phases. Based on the experimental results, the newly constructed HENSM model is very potential to be a new alternative in handling the overfitting issues of CML models and hence, can be used to predict the concrete CS, including the design of less polluting and more sustainable concrete constructions.

36 MATERIALS SCIENCE↗

Particle learning for probabilistic deterministic finite automata

The plpdfa software is a product of an LDRD project at LLNL entitked "Adaptive Sampling for Very High Throughput Data Streams" (tracking number 11-ERD-035). This software was developed by a graduate student summer intern, Chris Challis, who worked under project PI Dan Merl furing the summer of 2011. The software the source code is implementing is a statistical analysis technique for clustering and classification of text-valued data. The method had been previously published by the PI in the open literature.

Source record↗

Particle learning for probabilistic deterministic finite automata

The plpdfa software is a product of an LDRD project at LLNL entitked "Adaptive Sampling for Very High Throughput Data Streams" (tracking number 11-ERD-035). This software was developed by a graduate student summer intern, Chris Challis, who worked under project PI Dan Merl furing the summer of 2011. The software the source code is implementing is a statistical analysis technique for clustering and classification of text-valued data. The method had been previously published by the PI in the open literature.

Source record↗

Laterally Primed Adaptive Resonance Theory

LAPART is an artificial neural network algorithm written in the Python programming language. The algorithm can learn patterns using multi-dimensional hyper boxes. It can also perfrom regression and classification calculations based on learned associations.

Jones, Christian Birk↗

Traffic Signal Optimization by Integrating Reinforcement Learning and Digital Twins

Machine learning (ML) methods, especially reinforcement learning (RL), have been widely considered for traffic signal optimization in intelligent transportation systems. Most of these ML methods are centralized, lacking in scalability and adaptability in large traffic networks. Further, it is challenging to train such ML models due to the lack of training platforms and/or the cost of deploying and training in a real traffic networks. This paper presents an approach for the integration of decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin (DT) to optimize traffic signals for the reduction of traffic congestion and network-wide fuel consumption related to stopping. Specifically, the DGMARL agents learn traffic state patterns and make decisions regarding traffic signal control with assistance from a Digital Twin module, which simulates and replicates the traffic behaviors of a real traffic network. The proposed approach was evaluated using PTV-Vissim [1], a microscopic traffic simulation platform. PTV-Vissim is also the simulation engine of the DT, enabling emulation and optimization of the traffic signals on the MLK Smart Corridor in Chattanooga, Tennessee. Compared to an actuated signal control baseline approach, experiment results show that Eco_PI, a developed performance measure capturing the impact of stops on fuel consumption, was reduced by 44.27% in a 24-hour and an average of 29.88% in a PM-peak-hour scenario.

Multi-Agent Reinforcement Learning, Digital Twin, ↗

Adaptive Effects on Locomotion Performance Following Exposure to a Rotating Virtual Environment

During long-duration spaceflight, astronauts experience alterations in vestibular and somatosensory cues that result in adaptive disturbances in balance and coordination upon return to Earth. These changes can pose a risk to crew safety and to mission objectives if nominal or emergency vehicle egress is required immediately following long-duration spaceflight. At present, no operational countermeasure is available to mitigate the adaptive sensorimotor component underlying the locomotor disturbances that occur after spaceflight. Therefore, the goal of this study is to develop an inflight training regimen that facilitates recovery of locomotor function after long-duration spaceflight. The countermeasure we are proposing is based on the concept of adaptive generalization. During this type of training the subject gains experience producing the appropriate adaptive motor behavior under a variety of sensory conditions and response constraints. As a result of this training a subject learns to solve a class of motor problems, rather than a specific motor solution to one problem, i.e., the subject learns response generalizability or the ability to "learn to learn." under a variety of environmental constraints. We are developing an inflight countermeasure built around treadmill exercise activities. By manipulating the sensory conditions of exercise by varying visual flow patterns, body load and speed we will systematically and repeatedly promote adaptive change in locomotor behavior. It has been shown that variable practice training increases adaptability to novel visuo-motor situations. While walking over ground in a stereoscopic virtual environment that oscillated in roll, subjects have shown compensatory torso rotation in the direction of scene rotation that resulted in positional variation away from a desired linear path. Thus, postural sway and locomotor stability in 1-g can be modulated by visual flow patterns and used during inflight treadmill training to promote adaptive generalization. The purpose of this study was to determine if adaptive modification in locomotor performance could be achieved by viewing simulated self-motion in a passive-immersive virtual ' environment over a prolonged period during treadmill locomotion.

Mulavara, A. P.↗