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 505 records · Page 28

$\mathrm{SageNet}$: Fast Neural Network Emulation of the Stiff-amplified Gravitational Waves from Inflation

Accurate modeling of the inflationary gravitational waves (GWs) requires time-consuming, iterative numerical integrations of differential equations to take into account their backreaction on the expansion history. To improve computational efficiency while preserving accuracy, we present the Stiff-amplified Gravitational-wave Emulator Network (SageNet), a deep learning framework designed to replace conventional numerical solvers (code available at https://github.com/YifangLuo/SageNet). SageNet employs a long short-term memory architecture to emulate the present-day energy density spectrum of the inflationary GWs with possible stiff amplification, Ω GW (f). Trained on a data set of 25,689 numerically generated solutions, SageNet allows accurate reconstructions of Ω GW (f) and generalizes well to a wide range of cosmological parameters; 90.9% of the test emulations with randomly distributed parameters exhibit errors of under 4%. In addition, SageNet demonstrates its ability to learn and reproduce the artificial, adaptive sampling patterns in numerical calculations, which implement denser sampling of frequencies around changes in spectral indices in Ω GW (f). The dual capability of learning both physical and artificial features of the numerical GW spectra establishes SageNet as a robust alternative to exact numerical methods. Finally, our benchmark tests show that SageNet reduces the computation time from tens of seconds to milliseconds, achieving a speedup of ∼10 4 times over standard CPU-based numerical solvers with the potential for further acceleration on GPU hardware. These capabilities make SageNet a powerful tool for accelerating Bayesian inference procedures for extended cosmological models. In a broad sense, the SageNet framework offers a fast, accurate, and generalizable solution to modeling cosmological observables whose theoretical predictions demand costly differential equation solvers.

Astronomy data modeling↗

Development of Collaborative Research Initiatives to Advance the Aerospace Sciences-via the Communications, Electronics, Information Systems Focus Group

The primary goal of the Adaptive Vision Laboratory Research project was to develop advanced computer vision systems for automatic target recognition. The approach used in this effort combined several machine learning paradigms including evolutionary learning algorithms, neural networks, and adaptive clustering techniques to develop the E-MOR.PH system. This system is capable of generating pattern recognition systems to solve a wide variety of complex recognition tasks. A series of simulation experiments were conducted using E-MORPH to solve problems in OCR, military target recognition, industrial inspection, and medical image analysis. The bulk of the funds provided through this grant were used to purchase computer hardware and software to support these computationally intensive simulations. The payoff from this effort is the reduced need for human involvement in the design and implementation of recognition systems. We have shown that the techniques used in E-MORPH are generic and readily transition to other problem domains. Specifically, E-MORPH is multi-phase evolutionary leaming system that evolves cooperative sets of features detectors and combines their response using an adaptive classifier to form a complete pattern recognition system. The system can operate on binary or grayscale images. In our most recent experiments, we used multi-resolution images that are formed by applying a Gabor wavelet transform to a set of grayscale input images. To begin the leaming process, candidate chips are extracted from the multi-resolution images to form a training set and a test set. A population of detector sets is randomly initialized to start the evolutionary process. Using a combination of evolutionary programming and genetic algorithms, the feature detectors are enhanced to solve a recognition problem. The design of E-MORPH and recognition results for a complex problem in medical image analysis are described at the end of this report. The specific task involves the identification of vertebrae in x-ray images of human spinal columns. This problem is extremely challenging because the individual vertebra exhibit variation in shape, scale, orientation, and contrast. E-MORPH generated several accurate recognition systems to solve this task. This dual use of this ATR technology clearly demonstrates the flexibility and power of our approach.

Knasel, T. Michael↗

Harnessing Collaborative Learning Automata to Guide Multi-objective Optimization based Inverse Analysis for Structural Damage Identification

Structural damage identification based on physical models is often transformed into an optimization problem that minimizes the difference between measurement information of structure being monitored and the model prediction in the parametric space. However, the objective function in this context often exhibits multimodality, involving high-dimensional variables due to the reliance on finite element models for damage identification. These features pose challenges to optimization algorithms, where entrapment in local solutions can lead to false positives and false negatives in damage identification. In this research, we propose a reinforcement learning based multi-swarm optimizer to tackle such challenges in pursuit of a small yet diverse solution set that can capture the true damage scenario as one of the solutions. The proposed method leverages the flexibility of the particle swarm optimizer and incorporates novel strategies of metaheuristics to realize targeted improvement. To enable the particle swarm to adaptively select the appropriate search strategy based on the current environment, we adopt the learning automata technique, which sidesteps the need for reward strategy selection that is usually ad hoc at each step of the search. The integration harnesses the automatic learning and self-adaptation capabilities of learning automata, enabling the particles to navigate based on environmental signals. This leads to accumulated probabilities tied to advantageous movements, fostering an adaptive exploration of particles in the search space. The proposed approach is first validated through implementing into benchmark test cases with comparisons. It is then applied to structural damage identification with piezoelectric admittance experimental signals. `The results highlight the capability of the algorithm to identify a small solution set with high accuracy to match the actual damage scenario.

Yang Zhang↗

Highest fusion performance without harmful edge energy bursts in tokamak

The path of tokamak fusion and International thermonuclear experimental reactor (ITER) is maintaining high-performance plasma to produce sufficient fusion power. This effort is hindered by the transient energy burst arising from the instabilities at the boundary of plasmas. Conventional 3D magnetic perturbations used to suppress these instabilities often degrade fusion performance and increase the risk of other instabilities. This study presents an innovative 3D field optimization approach that leverages machine learning and real-time adaptability to overcome these challenges. Implemented in the DIII-D and KSTAR tokamaks, this method has consistently achieved reactor-relevant core confinement and the highest fusion performance without triggering damaging bursts. This is enabled by advances in the physics understanding of self-organized transport in the plasma edge and machine learning techniques to optimize the 3D field spectrum. The success of automated, real-time adaptive control of such complex systems paves the way for maximizing fusion efficiency in ITER and beyond while minimizing damage to device components.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Intelligent fault-tolerant controllers

A system with fault tolerant controls is one that can detect, isolate, and estimate failures and perform necessary control reconfiguration based on this new information. Artificial intelligence (AI) is concerned with semantic processing, and it has evolved to include the topics of expert systems and machine learning. This research represents an attempt to apply AI to fault tolerant controls, hence, the name intelligent fault tolerant control (IFTC). A generic solution to the problem is sought, providing a system based on logic in addition to analytical tools, and offering machine learning capabilities. The advantages are that redundant system specific algorithms are no longer needed, that reasonableness is used to quickly choose the correct control strategy, and that the system can adapt to new situations by learning about its effects on system dynamics.

Huang, Chien Y.↗

Virtual to Physical: Reinforcement Learning to Optimize SNS Particle Accelerator Controls

Complex accelerators must have control systems that can handle dynamic nonlinear environments. This makes traditional control methods unsuitable as they can struggle to adapt to these uncertainties. This provides an ideal environment for reinforcement learning algorithms as they are adaptable and generalizable. We present a reinforcement learning pipeline that can effectively handle the dynamics of a complex accelerator. We test and prove our pipelines capabilities on multiple environments including the Spallation Neutron Source (SNS) and the Beam Test Facility (BTF) at Oakridge National Lab (ORNL). Due to the limited time available to train an online algorithm like reinforcement learning on a real accelerator, we utilize a virtual twin accelerator (VIRAC) developed by ORNL to pretrain the policy and show its ability to converge in the virtual environment. We then test the adaptability of the pretrained RL model by applying it on the real accelerator and comparing the results. Utilizing our Scientific Optimization and Controls Toolkit (SOCT) and open-source standards such as Gymnasium we create and solve for a MEBT orbit correction problem in the SNS and an emittance maximization problem in the BTF. We show how Twin Delayed Deep Deterministic Policy Gradient (TD3) can solve this optimization environment in the virtual accelerator and transfer this policy onto the real accelerator for inference and model retraining. We show how reinforcement learning can be utilized as a control system for complex accelerators and provide a model pipeline for how an implementation performs and can be adapted to new accelerator control problems.

Kasparian, Armen [Thomas Jefferson National Accele↗

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

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

Engineering↗

Prediction of atomization energy using graph kernel and active learning

Data-driven prediction of molecular properties presents unique challenges to the design of machine learning methods concerning data structure/dimensionality, symmetry adaption, and confidence management. In this paper, we present a kernel-based pipeline that can learn and predict the atomization energy of molecules with high accuracy. The framework employs Gaussian process regression to perform predictions based on the similarity between molecules, which is computed using the marginalized graph kernel. To apply the marginalized graph kernel, a spatial adjacency rule is first employed to convert molecules into graphs whose vertices and edges are labeled by elements and interatomic distances, respectively. We then derive formulas for the efficient evaluation of the kernel. Specific functional components for the marginalized graph kernel are proposed, while the effects of the associated hyperparameters on accuracy and predictive confidence are examined. We show that the graph kernel is particularly suitable for predicting extensive properties because its convolutional structure coincides with that of the covariance formula between sums of random variables. Using an active learning procedure, we demonstrate that the proposed method can achieve a mean absolute error of 0.62 ± 0.01 kcal/mol using as few as 2000 training samples on the QM7 dataset.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Neural network with dynamically adaptable neurons

This invention is an adaptive neuron for use in neural network processors. The adaptive neuron participates in the supervised learning phase of operation on a co-equal basis with the synapse matrix elements by adaptively changing its gain in a similar manner to the change of weights in the synapse IO elements. In this manner, training time is decreased by as much as three orders of magnitude.

Tawel, Raoul↗

A Reinforcement Learning Approach to Parameter Selection for Distributed Optimal Power Flow

With the increasing penetration of distributed energy resources, distributed optimization algorithms have attracted significant attention for power systems applications due to their potential for superior scalability, privacy, and robustness to a single point-of-failure. The Alternating Direction Method of Multipliers (ADMM) is a popular distributed optimization algorithm; however, its convergence performance is highly dependent on the selection of penalty parameters, which are usually chosen heuristically. In this work, we use reinforcement learning (RL) to develop an adaptive penalty parameter selection policy for alternating current optimal power flow (ACOPF) problem solved via ADMM with the goal of minimizing the number of iterations until convergence. We train our RL policy using deep Q-learning and show that this policy can result in significantly accelerated convergence (up to a 59% reduction in the number of iterations compared to existing, curvatureinformed penalty parameter selection methods). Furthermore, we show that our RL policy demonstrates promise for generalizability, performing well under unseen loading schemes as well as under unseen losses of lines and generators (up to a 50% reduction in iterations). This work thus provides a proof-of-concept for using RL for parameter selection in ADMM for power systems applications.

alternating current optimal power flow↗

Controlling optical-cavity locking using reinforcement learning

Abstract This study applies an effective methodology based on Reinforcement Learning to a control system. Using the Pound–Drever–Hall locking scheme, we match the wavelength of a controlled laser to the length of a Fabry-Pérot cavity such that the cavity length is an exact integer multiple of the laser wavelength. Typically, long-term drift of the cavity length and laser wavelength exceeds the dynamic range of this control if only the laser’s piezoelectric transducer is actuated, so the same error signal also controls the temperature of the laser crystal. In this work, we instead implement this feedback control grounded on Q-Learning. Our system learns in real-time, eschewing reliance on historical data, and exhibits adaptability to system variations post-training. This adaptive quality ensures continuous updates to the learning agent. This innovative approach maintains lock for eight days on average.

47 OTHER INSTRUMENTATION↗

Automatic learning rate adjustment for self-supervising autonomous robot control

Described is an application in which an Artificial Neural Network (ANN) controls the positioning of a robot arm with five degrees of freedom by using visual feedback provided by two cameras. This application and the specific ANN model, local liner maps, are based on the work of Ritter, Martinetz, and Schulten. We extended their approach by generating a filtered, average positioning error from the continuous camera feedback and by coupling the learning rate to this error. When the network learns to position the arm, the positioning error decreases and so does the learning rate until the system stabilizes at a minimum error and learning rate. This abolishes the need for a predetermined cooling schedule. The automatic cooling procedure results in a closed loop control with no distinction between a learning phase and a production phase. If the positioning error suddenly starts to increase due to an internal failure such as a broken joint, or an environmental change such as a camera moving, the learning rate increases accordingly. Thus, learning is automatically activated and the network adapts to the new condition after which the error decreases again and learning is 'shut off'. The automatic cooling is therefore a prerequisite for the autonomy and the fault tolerance of the system.

Arras, Michael K.↗

Locomotor Dysfunction after Spaceflight: Characterization and Countermeasure Development

Astronauts returning from space flight show disturbances in locomotor control manifested by changes in various sub-systems including head-trunk coordination, dynamic visual acuity, lower limb muscle activation patterning and kinematics (Glasauer, et al., 1995; Bloomberg, et al., 1997; McDonald, et al., 1996; 1997; Layne, et al., 1997; 1998, 2001, 2004; Newman, et al., 1997; Bloomberg and Mulavara, 2003). These post flight changes in locomotor performance, due to neural adaptation to the microgravity conditions of space flight, affect the ability of crewmembers especially after a long duration mission to egress their vehicle and perform extravehicular activities soon after landing on Earth or following a landing on the surface of the Moon or Mars. At present, no operational training intervention is available pre- or in- flight to mitigate post flight locomotor disturbances. Our laboratory is currently developing a gait adaptability training program that is designed to facilitate recovery of locomotor function following a return to a gravitational environment. The training program exploits the ability of the sensorimotor system to generalize from exposure to multiple adaptive challenges during training so that the gait control system essentially "learns to learn" and therefore can reorganize more rapidly when faced with a novel adaptive challenge. Ultimately, the functional goal of an adaptive generalization countermeasure is not necessarily to immediately return movement patterns back to "normal". Rather the training regimen should facilitate the reorganization of available sensorimotor sub-systems to achieve safe and effective locomotion as soon as possible after space flight. We have previously confirmed that subjects participating in adaptive generalization training programs, using a variety of visuomotor distortions and different motor tasks from throwing to negotiating an obstacle course as the dependent measure, can learn to enhance their ability to adapt to a novel sensorimotor environment (Roller et al., 2001; Cohen et al. 2005). Importantly, this increased adaptability is retained even one month after completion of the training period. Our laboratory is currently developing adaptive generalization training procedures and the associated flight hardware to implement such a training program, using variations of visual flow, subject loading, and treadmill speed; during regular in-flight treadmill operations.

Mulavara, A. P.↗

Multiresolution convolutional autoencoders

Herein we propose a multi-resolution convolutional autoencoder (MrCAE) architecture that integrates and leverages three highly successful mathematical architectures: (i) multigrid methods, (ii) convolutional autoencoders and (iii) transfer learning. The method provides an adaptive, hierarchical architecture that capitalizes on a progressive training approach for multiscale spatio-temporal data. This framework allows for inputs across multiple scales: starting from a compact (small number of weights) network architecture and low-resolution data, our network progressively deepens and widens itself in a principled manner to encode new information in the higher resolution data based on its current performance of reconstruction. Basic transfer learning techniques are applied to ensure information learned from previous training steps can be rapidly transferred to the larger network. As a result, the network can dynamically capture different scaled features at different depths of the network. The performance gains of this adaptive multiscale architecture are illustrated through a sequence of numerical experiments on synthetic examples and real-world spatial-temporal data.

97 MATHEMATICS AND COMPUTING↗

Development of a Countermeasure to Mitigate Postflight Locomotor Dysfunction

Astronauts returning from space flight experience locomotor dysfunction following their return to Earth. Our laboratory is currently developing a gait adaptability training program that is designed to facilitate recovery of locomotor function following a return to a gravitational environment. The training program exploits the ability of the sensorimotor system to generalize from exposure to multiple adaptive challenges during training so that the gait control system essentially learns to learn and therefore can reorganize more rapidly when faced with a novel adaptive challenge. Evidence for the potential efficacy of an adaptive generalization gait training program can be obtained from numerous studies in the motor learning literature which have demonstrated that systematically varying the conditions of training enhances the ability of the performer to learn and retain a novel motor task. These variable practice training approaches have been used in applied contexts to improve motor skills required in a number of different sports. The central nervous system (CNS) can produce voluntary movement in an almost infinite number of ways. For example, locomotion can be achieved with many different combinations of joint angles, muscle activation patterns and forces. The CNS can exploit these degrees of freedom to enhance motor response adaptability during periods of adaptive flux like that encountered during a change in gravitational environment. Ultimately, the functional goal of an adaptive generalization countermeasure is not necessarily to immediately return movement patterns back to normal. Rather the training regimen should facilitate the reorganization of available sensory and motor subsystems to achieve safe and effective locomotion as soon as possible after long duration space flight. Indeed, this approach has been proposed as a basic feature underlying effective neurological rehabilitation. We have previously confirmed that subjects participating in an adaptive generalization training program using a variety of visuomotor distortions and throwing as the dependent measure can learn to enhance their ability to adapt to a novel sensorimotor environment (Roller et al., 2001). Importantly, this increased adaptability was retained even one month after completion of the training period. Adaptive generalization has been observed in a variety of other tasks requiring sensorimotor transformations including manual control tasks and reaching (Bock et al., 2001, Seidler, 2003) and obstacle avoidance during walking (Lam and Dietz, 2004). Taken together, the evidence suggests that a training regimen exposing crewmembers to variation in locomotor conditions, with repeated transitions among states, may enhance their ability to learn how to reassemble appropriate locomotor patterns upon return from microgravity. We believe exposure to this type of training will extend crewmembers locomotor behavioral repertoires, facilitating the return of functional mobility after long duration space flight. In other words, our proposed training protocol will compel subjects to develop new behavioral solutions under varying sensorimotor demands. Over time subjects will learn to create appropriate locomotor solution more rapidly enabling acquisition of mobility sooner after long-duration space flight. A gait adaptability training program can be superimposed on nominal treadmill exercise activities thus ensuring that no additional crew time is required to perform this type of training regimen and that it can be implemented with current in-flight exercise systems available on the International Space Station.

Bloomberg, J. J.↗

Hardware Acceleration of Adaptive Neural Algorithms.

As tradit ional numerical computing has faced challenges, researchers have turned towards alternative computing approaches to reduce power - per - computation metrics and improve algorithm performance. Here, we describe an approach towards non - conventional computing that strengthens the connection between machine learning and neuroscience concepts. The Hardware Acceleration of Adaptive Neural Algorithms (HAANA) project ha s develop ed neural machine learning algorithms and hardware for applications in image processing and cybersecurity. While machine learning methods are effective at extracting relevant features from many types of data, the effectiveness of these algorithms degrades when subjected to real - world conditions. Our team has generated novel neural - inspired approa ches to improve the resiliency and adaptability of machine learning algorithms. In addition, we have also designed and fabricated hardware architectures and microelectronic devices specifically tuned towards the training and inference operations of neural - inspired algorithms. Finally, our multi - scale simulation framework allows us to assess the impact of microelectronic device properties on algorithm performance.

97 MATHEMATICS AND COMPUTING↗