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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
NASA NTRS1998

Role of the flocculus of the cerebellum in motor learning of the vestibulo-ocular reflex

Structure-function studies at the systems level are an effective method for understanding the relationship of the central nervous system to behavior. Motor learning or adaptation of the vestibulo-ocular reflex is a clear example wherein this approach has been productive. During a vestibulo-ocular reflex the brain converts a head velocity signal, transduced through the vestibular semicircular canals, into an eye movement command delivered to the extraocular muscles. If the viewed target remains on the fovea of the retina, the reflex is compensatory, and its gain, eye velocity/head velocity, is one. When the image of the viewed object slips across the retina, visual acuity decreases, and the gain of the reflex, which is no longer one, is plastically adapted or adjusted until retinal stability is restored. The anatomic substrate for this plasticity thus involves brain structures in which visual-vestibular interaction can potentially occur, as well as vestibular and visual sensory and oculomotor motor structures. Further, it has been known for many years that removal of the flocculus of the cerebellum permanently precludes further vestibulo-ocular reflex adaptation, demonstrating the involvement of the cerebellum in this behavior. Maekawa and Simpson (J Neurophysiol 1973;36: 649-66) discovered that one visual input to the flocculus involved the accessory optic system and the inferior olive. Ensuing work has demonstrated that the visual signals used to adapt the vestibulo-ocular reflex are transmitted by this accessory optic system to the flocculus and subsequently to brain stem structures involved in vestibulo-ocular reflex plasticity. Presently the inclusive list of anatomic sites involved in vestibulo-ocular reflex circuitry and its adaptive plasticity is small. Our laboratory continues to believe that this behavior should be caused by interactions within this small class of neurons. By studying each class of identified neuron and its interactions with others within the list, we hope to ultimately understand the mechanisms used by the brain in the expression of this behavior.

Non-NASA Center↗
NASA NTRS2005

Development of Advanced Verification and Validation Procedures and Tools for the Certification of Learning Systems in Aerospace Applications

Adaptive control technologies that incorporate learning algorithms have been proposed to enable automatic flight control and vehicle recovery, autonomous flight, and to maintain vehicle performance in the face of unknown, changing, or poorly defined operating environments. In order for adaptive control systems to be used in safety-critical aerospace applications, they must be proven to be highly safe and reliable. Rigorous methods for adaptive software verification and validation must be developed to ensure that control system software failures will not occur. Of central importance in this regard is the need to establish reliable methods that guarantee convergent learning, rapid convergence (learning) rate, and algorithm stability. This paper presents the major problems of adaptive control systems that use learning to improve performance. The paper then presents the major procedures and tools presently developed or currently being developed to enable the verification, validation, and ultimate certification of these adaptive control systems. These technologies include the application of automated program analysis methods, techniques to improve the learning process, analytical methods to verify stability, methods to automatically synthesize code, simulation and test methods, and tools to provide on-line software assurance.

Jacklin, Stephen↗
DOE OSTI2019

Memristor design rules for dynamic learning and edge processing applications

The ability to dynamically learn and adapt to changes in the environment is one of the hallmarks of biological systems. In this work, we identify the subset of the design space of memristive materials that is optimal for dynamic learning applications. Using an architecture inspired on the learning center of the insect brain, we implement a model system consisting of a discrete implementation of spiking neurons where dynamic learning takes place on a set of plastic synapses formed by memristor pairs in a crossbar array. Using two separate benchmarks, one comprising the dynamic learning of the Modified National Institute of Standards and Technology dataset and another one targeting one shot learning, we have identified the key properties that memristive materials should have to be optimal dynamic learners. The results obtained show that a fine degree of control of the memristor internal state is key to achieve high classification accuracy during dynamic learning but that within this optimal region learning is extremely robust both to device variability and to errors in the writing of the internal state, in all cases allowing for 2 sigma variations greater than 40% without significant loss of accuracy, hence overcoming two of the perceived limitations of memristors. By additionally requiring that learning takes place concurrently to information processing, we are able to derive a set constraints to the memristor dynamics.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Tyramine and its Amtyr1 receptor modulate attention in honey bees (Apis mellifera)

Animals must learn to ignore stimuli that are irrelevant to survival and attend to ones that enhance survival. When a stimulus regularly fails to be associated with an important consequence, subsequent excitatory learning about that stimulus can be delayed, which is a form of nonassociative conditioning called ‘latent inhibition’. Honey bees show latent inhibition toward an odor they have experienced without association with food reinforcement. Moreover, individual honey bees from the same colony differ in the degree to which they show latent inhibition, and these individual differences have a genetic basis. To investigate the mechanisms that underly individual differences in latent inhibition, we selected two honey bee lines for high and low latent inhibition, respectively. We crossed those lines and mapped a Quantitative Trait Locus for latent inhibition to a region of the genome that contains the tyramine receptor gene Amtyr1 [We use Amtyr1 to denote the gene and AmTYR1 the receptor throughout the text.]. We then show that disruption of Amtyr1 signaling either pharmacologically or through RNAi qualitatively changes the expression of latent inhibition but has little or slight effects on appetitive conditioning, and these results suggest that AmTYR1 modulates inhibitory processing in the CNS. Electrophysiological recordings from the brain during pharmacological blockade are consistent with a model that AmTYR1 indirectly regulates at inhibitory synapses in the CNS. Our results therefore identify a distinct Amtyr1 -based modulatory pathway for this type of nonassociative learning, and we propose a model for how Amtyr1 acts as a gain control to modulate hebbian plasticity at defined synapses in the CNS. We have shown elsewhere how this modulation also underlies potentially adaptive intracolonial learning differences among individuals that benefit colony survival. Finally, our neural model suggests a mechanism for the broad pleiotropy this gene has on several different behaviors.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2011

Flight Test Approach to Adaptive Control Research

The National Aeronautics and Space Administration s Dryden Flight Research Center completed flight testing of adaptive controls research on a full-scale F-18 testbed. The validation of adaptive controls has the potential to enhance safety in the presence of adverse conditions such as structural damage or control surface failures. This paper describes the research interface architecture, risk mitigations, flight test approach and lessons learned of adaptive controls research.

Pavlock, Kate Maureen↗
DOE OSTI2017

Building an Adaptive Optics Demonstrator System

Adaptive optics is used to correct the wavefront of a beam of light. It originated in the field of astronomy to correct for atmospheric turbulence. This project was to construct an adaptive optics (AO) system kit from Thorlabs. An AO system consists of three parts: a deformable mirror (DM), a wavefront sensor (WFS), and control software. This system is to be used for future teaching purposes to help others learn about adaptive optics. The AO system came with instruction manuals, which were followed to build and calibrate the system. The instructions included building and aligning the system, how to install and use the software, and how to calibrate deformable mirror. A calibrated system for this project means having the deformable mirror imaged onto the wavefront sensor, with the center of the mirror on the center of the WFS. Also, a flat wavefront, which is achieved by eliminating the tip/tilt of the mirror. Eliminating the tip/tilt reduces the RMS amplitude to a value below 0.200 microns. This causes the wavefront to fold in on itself. We set up a focal plane detector behind beam splitter as a demonstration of what would be seen if this were used with a telescope. The image that should be seen on the focal plane detector is the beam with a diffraction pattern called and Airy Function. The AO system is now ready to be used to teach others about adaptive optics.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Multi-Objective Adaptive Mesh Refinement Using Reinforcement Learning

Finite element methods approximate the solution to a partial differential equation (PDE) on a mesh consisting of many elements. In general, using more, smaller elements results in a lower error in the approximation. However, it is often possible to lower the error substantially by only refining, or decreasing the size of, the few elements in the mesh that have the highest error. Adaptive mesh refinement (AMR) is a process that selectively refines regions of a mesh with high error to achieve a desired accuracy in as few degrees of freedom (DOFs) as possible. AMR is favorable compared to uniform refinement, which refines all elements of the mesh equally, because it can often achieve the same accuracy without wasting extra computation time on refinement of elements that already have low error. However, it is difficult to know which elements to refine. In this report we explore ways to choose which elements to refine such that we minimize both the resulting error and the cumulative DOFs used in computation. In particular, we introduce a Pareto-front learning algorithm that trains a policy to give the optimal refinement actions to minimize the cumulative DOFs used to achieve a given target error. Such a policy is useful because it can be deployed on many different problem types where different accuracy levels are desired. Furthermore, training a single policy for a range of target errors allows us to use transfer learning to reduce the required training time.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2011

Flight Approach to Adaptive Control Research

The National Aeronautics and Space Administration's Dryden Flight Research Center completed flight testing of adaptive controls research on a full-scale F-18 testbed. The testbed served as a full-scale vehicle to test and validate adaptive flight control research addressing technical challenges involved with reducing risk to enable safe flight in the presence of adverse conditions such as structural damage or control surface failures. This paper describes the research interface architecture, risk mitigations, flight test approach and lessons learned of adaptive controls research.

Pavlock, Kate Maureen↗
DOE OSTI2026

PowerModelsGAT-AI: Physics-Informed Graph Attention for Multi-System Power Flow With Continual Learning

Solving the alternating current power flow equations in real time is essential for secure grid operation, yet classical Newton–Raphson solvers can be slow under stressed conditions. Existing graph neural networks for power flow are typically trained on a single system and often degrade on different systems. We present PowerModelsGAT-AI, a physics-informed graph attention network that predicts bus voltages and generator injections. The model uses bus-type-aware masking to handle different bus types and balances multiple loss terms, including a power-mismatch penalty, using learned weights. We evaluate the model on 14 benchmark systems (4 to 6,470 buses) and train a unified model on 13 of these under contingency conditions with up to two branch outages, achieving an average normalized mean absolute error of 0.89% for voltage magnitudes and R 2 >0.99 for voltage angles. We also show continual learning: when adapting a base model to a new 1,354-bus system, standard fine-tuning causes severe forgetting with error increases exceeding 1000% on base systems, while our experience replay and elastic weight consolidation strategy keeps error increases below 2% and in some cases improves base-system performance. Interpretability analysis shows that learned attention weights correlate with physical branch parameters (susceptance: r=0.38 ; thermal limits: r=0.22 ), and feature importance analysis supports that the model captures established power flow relationships.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Entropy and Boundary Based Adversarial Learning for Large Scale Unsupervised Domain Adaptation

Supervised semantic segmentation methods provide state-of-the-art performance, but their performance is limited by the amount of quality labeled data they need for training. Scarcity of labeled data and non-transferablity of models, due to cross-domain discrepancy makes it a bigger challenge for remote sensing imagery analysis. In this work, we approach this problem through adversarial learning, driven by entropy and boundary of region-of-interest for unsupervised domain adaptation. This concept helps with better boundary prediction and encourages target domain entropy maps (probability/uncertainty maps) to be similar to source domains. In particular, we showed that deriving informative entropy through the adversarial learning is essential to enable the adaptation. We used a large scale cross country building extraction dataset to validate the framework. The experimental results show the usefulness of considering boundary and entropy driven adversarial learning for adaptation.

Makkar, Nikhil↗
NASA NTRS2024

Artificial Intelligence Medical Support for Long-Duration Space Missions

We envision an artificial intelligence (AI) based system that will provide support and recommendations to the crew medical officer (CMO) and ground flight surgeon during long-duration space missions. Such a system would be pretrained on the knowledgebase of clinical knowledge on Earth, minimizing the amount of Earth data that needs to be transferred into space. Then during deployment, the system would be constantly refined through active learning from diverse streams of data from sensors in the spacecraft, data collected daily from individual astronauts, and human-in-the-loop feedback from the crew. The model could be interrogated for predictions and recommendations on personalized crew health based on the overall status of the spacecraft, medicinal stores, and status of other crew members. Adaptation techniques would be used to incorporate spaceflight data that have very different distributions from the training data due to the extreme environment. Edge computing and the most advanced neuromorphic processing would enable computation in scenarios with low power and bandwidth, while dimensionality reduction would be employed to ensure that the input data streams from spaceflight are as small as possible. In order to realize this long-term vision, several hardware and software aspects need to be developed and assembled. First, models pretrained on Earth biomedical data would need to be evaluated for predictive accuracy, and the best one selected. That model would need to be adapted to learn from diverse, sparse, and inconsistently measured data streams, as well as human-in-the-loop feedback. A data integration, standardization, and dimensionality reduction methodology would need to be developed to handle all data types and feed them into the model. Once the software and data infrastructure is developed, it would need to be integrated with small footprint compute processors and tested in high-radiation, high-vibration, unregulated temperature situations. As a short-term goal, we recommend to focus on the development of the data and model software structure. Several large language models (LLM) already exist that have been trained on Earth biomedical and clinical knowledgebases, including BioMedLLM, Med-PaLM, SPOKE LLM, and Foresight. These models need to be evaluated for accuracy and the best one chosen for a proof-of-concept structure, while maintaining awareness of the accelerating AI field and incorporating any newly improved model architectures as needed. Then, we recommend to develop a database of synthetic data types to mimic the diverse data streams that are expected in a long-duration space mission. This should include environmental and microbial data from the spacecraft, non-invasive data from wearables and point-of-care devices employed by astronauts, and more invasive molecular and physiological monitoring of clinical and biomarker data from astronauts. The data standardization methodology should be developed, and these data streams used to refine the clinical LLM. Several scenarios should be developed that could plausibly come up in a long-duration space mission, and changes or aberrations introduced to the data at specific times to mimic these scenarios. Then, question and answer tasks should be designed to interrogate the model for predictions and recommendations, with acceptable answers already identified.

Artificial Intelligence↗
NASA NTRSDate not supplied

Adaptive Stress Testing: Using Reinforcement Learning to Find Failures in Safety-Critical Systems

Emerging applications in artificial intelligence, such as driverless cars and autonomous aircraft promise to be more efficient, cheaper to operate, and always available. However, ensuring the safety of these systems remains a major challenge to their certification and adoption. These autonomous systems are expected to routinely make safety-critical decisions where failures can have serious consequences including loss of life and property. Testing and validation techniques aim to identify and diagnose potential failures before the system is deployed. However, finding failure scenarios in autonomous systems can be very challenging due to high-dimensional and continuous state spaces, interaction with large environments over many time steps, and the rarity of failures. This talk presents Adaptive Stress Testing (AST), a simulation-based testing framework for finding the most likely path to a failure event of a safety-critical system. The key idea of AST is that stress testing can be formulated as a Partially Observable Markov Decision Process (POMDP), which enables reinforcement learning techniques to be used for finding failure events. Reinforcement learning algorithms can efficiently explore the search space and have been shown to scale to very large systems. We present applications of AST to find failures in various safety-critical systems including the aircraft collision avoidance systems, autonomous cars, and small unmanned aerial vehicles.

autonomous vehicles↗
DOE OSTI2025

Adaptive Client Selection in Federated Learning: A Network Anomaly Detection Use Case

Federated Learning (FL) has become a ubiquitous approach for training machine learning models on decentralized data, addressing the myriad privacy concerns inherent in traditional centralized methods. However, the efficiency of FL depends on effective client selection and robust privacy preservation mechanisms. Inadequate client selection may lead to suboptimal model performance, while insufficient privacy measures risk exposing sensitive data. This paper proposes a client selection framework for FL that integrates differential privacy and fault tolerance. Our adaptive approach dynamically adjusts the number of selected clients based on model performance and system constraints, ensuring privacy through calibrated noise addition. We evaluate our method on a network anomaly detection use case using the UNSW-NB15 and ROAD datasets. Results show up to a 7% increase in accuracy and a 25% reduction in training time compared to FedL2P. Moreover, we highlight the trade-offs between privacy budgets and model performance, with higher privacy budgets reducing noise and improving accuracy. Our fault tolerance mechanism, while causing a slight performance drop, enhances robustness to client failures. Statistical validation using Mann-Whitney U tests confirms the significance of these improvements (p < 0.05).

Marfo, William [University of Texas at El Paso,Dep↗
DOE OSTI2021

Adaptive critic design-based reinforcement learning approach in controlling virtual inertia-based grid-connected inverters

In this report, an adaptive critic design (ACD) approach is proposed to control the phase and voltage of a grid-connected virtual synchronous generator (VSG). The penetration of fast responding inertia-less power converters significantly affect the stability of the power system, especially weak systems such as micro grids. The concept of virtual inertia addresses this concern by virtually emulating the behavior of a synchronous generator. However, the conventional VSG is designed based on two conditions: (i) fixed operating point and (ii) inductive grid connections. The performance of VSGs in low-voltage semi-resistive microgrids is far from optimal. To overcome the aforementioned concerns, a heuristic dynamic programing (HDP) approach is proposed to optimally control grid-connected VSGs. The neural-network-based inherence of the HDP enables the proposed technique to adapt to any impedance angle. The HDP controller includes two subnetworks: (i) the action network that controls the system optimally and (ii) the critic network, which evaluates the effectiveness of the action network. The simulation and experimental results are provided to evaluate the effectiveness of the proposed technique. As shown, the HDP-based approach illustrates a better performance in comparison with the conventional PI-based VSG in various operating conditions.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Receptance coupling substructure analysis and chatter frequency-informed machine learning for milling stability

This paper describes a milling stability identification approach that simultaneously considers: physics-based models for the tool tip frequency response functions and stability predictions; the binary result from a milling test (automatically labeled as stable or unstable based on frequency content); chatter frequency when an unstable result is obtained; and user risk tolerance. The algorithm applies probabilistic Bayesian machine learning with adaptive, parallelized Markov Chain Monte Carlo sampling to update the probability of stability with each milling test. Furthermore, the result is a robust solution for rapid convergence to optimized milling parameters for maximum metal removal rate using all available information.

42 ENGINEERING↗
NASA NTRS2011

Full-Scaled Advanced Systems Testbed: Ensuring Success of Adaptive Control Research Through Project Lifecycle Risk Mitigation

The National Aeronautics and Space Administration's Dryden Flight Research Center completed flight testing of adaptive controls research on the Full-Scale Advance Systems Testbed (FAST) in January of 2011. The research addressed technical challenges involved with reducing risk in an increasingly complex and dynamic national airspace. Specific challenges lie with the development of validated, multidisciplinary, integrated aircraft control design tools and techniques to enable safe flight in the presence of adverse conditions such as structural damage, control surface failures, or aerodynamic upsets. The testbed is an F-18 aircraft serving as a full-scale vehicle to test and validate adaptive flight control research and lends a significant confidence to the development, maturation, and acceptance process of incorporating adaptive control laws into follow-on research and the operational environment. The experimental systems integrated into FAST were designed to allow for flexible yet safe flight test evaluation and validation of modern adaptive control technologies and revolve around two major hardware upgrades: the modification of Production Support Flight Control Computers (PSFCC) and integration of two, fourth-generation Airborne Research Test Systems (ARTS). Post-hardware integration verification and validation provided the foundation for safe flight test of Nonlinear Dynamic Inversion and Model Reference Aircraft Control adaptive control law experiments. To ensure success of flight in terms of cost, schedule, and test results, emphasis on risk management was incorporated into early stages of design and flight test planning and continued through the execution of each flight test mission. Specific consideration was made to incorporate safety features within the hardware and software to alleviate user demands as well as into test processes and training to reduce human factor impacts to safe and successful flight test. This paper describes the research configuration, experiment functionality, overall risk mitigation, flight test approach and results, and lessons learned of adaptive controls research of the Full-Scale Advanced Systems Testbed.

Pavlock, Kate M.↗
DOE OSTI2016

Neurogenesis Deep Learning: Extending deep networks to accommodate new classes

Neural machine learning methods, such as deep neural networks (DNN), have achieved remarkable success in a number of complex data processing tasks. These methods have arguably had their strongest impact on tasks such as image and audio processing – data processing domains in which humans have long held clear advantages over conventional algorithms. In contrast to biological neural systems, which are capable of learning continuously, deep artificial networks have a limited ability for incorporating new information in an already trained network. As a result, methods for continuous learning are potentially highly impactful in enabling the application of deep networks to dynamic data sets. Here, inspired by the process of adult neurogenesis in the hippocampus, we explore the potential for adding new neurons to deep layers of artificial neural networks in order to facilitate their acquisition of novel information while preserving previously trained data representations. Our results on the MNIST handwritten digit dataset and the NIST SD 19 dataset, which includes lower and upper case letters and digits, demonstrate that neurogenesis is well suited for addressing the stability-plasticity dilemma that has long challenged adaptive machine learning algorithms.

59 BASIC BIOLOGICAL SCIENCES↗