SEARCH · Search NASA

Results for “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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17

All sources NASA NTRS DOE OSTI

DOE OSTI2026

Quantum-Inspired Bayesian Sampling for Uncertainty Quantification and Machine Learning (Final Technical Report)

With increasing simulation and measurement data, machine learning and artificial intelligence have been widely used in computational decision-making of complex engineering systems. The resulting tools, such as uncertainty quantification solvers, reinforcement learning, and physics-informed machine learning, have achieved great success in critical DOE tasks such as material discovery and design, energy system modeling and control, and numerical weather and climate prediction. A core topic in scientific machine learning and artificial intelligence is Bayesian inference: given an observed data set, people want to estimate the posterior distribution of a (possibly large) number of hidden parameters. Due to the flexibility and weak assumptions, Bayesian sampling has been the mainstream Bayesian inference solvers despite the rapid progress of approximate Bayesian inference. Classical Bayesian sampling methods such as Markov-chain Monte Carlo suffer from a low-acceptance rate due to the random walk nature, therefore state-of-the-art techniques use Hamiltonian Monte Carlo and its variants to efficiently draw posterior samples in a high dimension. The key idea of Hamiltonian Monte Carlo and its variants is to simulate the Hamiltonian dynamics of a classical particle with a fixed mass, and their performance significantly degrades when the posterior distribution is highly spiky or has multiple modes. Leveraging the idea of quantum physics, this project has investigated new theory, algorithms and applications of Bayesian inference (especially Bayesian sampling). The main results include: (1) novel quantum-inspired Bayesian sampling methods that can lead to better accuracy for challenging multi-modal or spiky distributions, (2) more scalable machine learning framework leveraging tensor-compressed Bayesian inference, and (3) Bayesian and sampling approaches for verifying the robustness of continuous and binary neural networks.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Scale-up Unlearnable Examples Learning with High-performance Computing

Recent advancements in AI models, like ChatGPT, are structured to retain user interactions, which could inadvertently include sensitive healthcare data. In the healthcare field, particularly when radiologists use AI-driven diagnostic tools hosted on online platforms, there is a risk that medical imaging data may be repurposed for future AI training without explicit consent, spotlighting critical privacy and intellectual property concerns around healthcare data usage. Addressing these privacy challenges, a novel approach known as Unlearnable Examples (UEs) has been introduced, aiming to make data unlearnable to deep learning models. A prominent method within this area, called Unlearnable Clustering (UC), has shown improved UE performance with larger batch sizes but was previously limited by computational resources (e.g., a single workstation). To push the boundaries of UE performance with theoretically unlimited resources, we scaled up UC learning across various datasets using Distributed Data Parallel (DDP) training on the Summit supercomputer. Our goal was to examine UE efficacy at high-performance computing (HPC) levels to prevent unauthorized learning and enhance data security, particularly exploring the impact of batch size on UE’s unlearnability. Utilizing the robust computational capabilities of the Summit, extensive experiments were conducted on diverse datasets such as Pets, MedMNist, Flowers, and Flowers102. Our findings reveal that both overly large and overly small batch sizes can lead to performance instability and affect accuracy. However, the relationship between batch size and unlearnability varied across datasets, highlighting the necessity for tailored batch size strategies to achieve optimal data protection. The use of Summit’s high-performance GPUs, along with the efficiency of the DDP framework, facilitated rapid updates of model parameters and consistent training across nodes. Our results underscore the critical role of selecting appropriate batch sizes based on the specific characteristics of each dataset to prevent learning and ensure data security in deep learning applications. The source code is publicly available at https: // github. com/ hrlblab/ UE_ HPC .

Zhu, Yanfan [Vanderbilt University, Nashville, TN,↗

DOE OSTI2024

Integrating multi-modal remote sensing, deep learning, and attention mechanisms for yield prediction in plant breeding experiments

In both plant breeding and crop management, interpretability plays a crucial role in instilling trust in AI-driven approaches and enabling the provision of actionable insights. The primary objective of this research is to explore and evaluate the potential contributions of deep learning network architectures that employ stacked LSTM for end-of-season maize grain yield prediction. A secondary aim is to expand the capabilities of these networks by adapting them to better accommodate and leverage the multi-modality properties of remote sensing data. In this study, a multi-modal deep learning architecture that assimilates inputs from heterogeneous data streams, including high-resolution hyperspectral imagery, LiDAR point clouds, and environmental data, is proposed to forecast maize crop yields. The architecture includes attention mechanisms that assign varying levels of importance to different modalities and temporal features that, reflect the dynamics of plant growth and environmental interactions. The interpretability of the attention weights is investigated in multi-modal networks that seek to both improve predictions and attribute crop yield outcomes to genetic and environmental variables. This approach also contributes to increased interpretability of the model's predictions. The temporal attention weight distributions highlighted relevant factors and critical growth stages that contribute to the predictions. The results of this study affirm that the attention weights are consistent with recognized biological growth stages, thereby substantiating the network's capability to learn biologically interpretable features. Accuracies of the model's predictions of yield ranged from 0.82-0.93 R 2 ref in this genetics-focused study, further highlighting the potential of attention-based models. Further, this research facilitates understanding of how multi-modality remote sensing aligns with the physiological stages of maize. The proposed architecture shows promise in improving predictions and offering interpretable insights into the factors affecting maize crop yields, while demonstrating the impact of data collection by different modalities through the growing season. By identifying relevant factors and critical growth stages, the model's attention weights provide valuable information that can be used in both plant breeding and crop management. The consistency of attention weights with biological growth stages reinforces the potential of deep learning networks in agricultural applications, particularly in leveraging remote sensing data for yield prediction. To the best of our knowledge, this is the first study that investigates the use of hyperspectral and LiDAR UAV time series data for explaining/interpreting plant growth stages within deep learning networks and forecasting plot-level maize grain yield using late fusion modalities with attention mechanisms.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Deep-learning-driven simulations of boundary layer clouds over the Southern Great Plains

Abstract. Based on long-term observations at the Southern Great Plains site by the Atmospheric Radiation Measurement (ARM) program for training and validation, a deep-learning model is developed to simulate the daytime evolution of boundary layer clouds (BLCs) from the perspective of land–atmosphere coupling. The model takes ARM measurements (including early-morning soundings and diurnally varying surface meteorological conditions and heat fluxes) as inputs and predicts hourly estimates (including cloud occurrence, the positions of cloud boundaries, and the vertical profile of the cloud fraction) as outputs. The deep-learning model offers good agreement with the observed cloud fields, especially in the accuracy with which cloud occurrence and base height are reproduced. When the inputs are substituted by reanalysis data from ERA5 and MERRA-2, the outputs of the deep-learning model provide a better agreement with observation than the cloud fields extracted from ERA5 and MERRA-2 themselves. Thus, the deep-learning model shows great potential to serve as a diagnostic tool for the performance of physics-based models in simulating stratiform and cumulus clouds. By quantifying biases in clouds and attributing them to the simulated atmospheric state variables versus the model-parameterized cloud processes, this observation-based deep-learning model may offer insights into the directions needed to improve the simulation of BLCs in physics-based models for weather forecasting and climate prediction.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS1988

Strategies for adding adaptive learning mechanisms to rule-based diagnostic expert systems

Rule-based diagnostic expert systems can be used to perform many of the diagnostic chores necessary in today's complex space systems. These expert systems typically take a set of symptoms as input and produce diagnostic advice as output. The primary objective of such expert systems is to provide accurate and comprehensive advice which can be used to help return the space system in question to nominal operation. The development and maintenance of diagnostic expert systems is time and labor intensive since the services of both knowledge engineer(s) and domain expert(s) are required. The use of adaptive learning mechanisms to increment evaluate and refine rules promises to reduce both time and labor costs associated with such systems. This paper describes the basic adaptive learning mechanisms of strengthening, weakening, generalization, discrimination, and discovery. Next basic strategies are discussed for adding these learning mechanisms to rule-based diagnostic expert systems. These strategies support the incremental evaluation and refinement of rules in the knowledge base by comparing the set of advice given by the expert system (A) with the correct diagnosis (C). Techniques are described for selecting those rules in the in the knowledge base which should participate in adaptive learning. The strategies presented may be used with a wide variety of learning algorithms. Further, these strategies are applicable to a large number of rule-based diagnostic expert systems. They may be used to provide either immediate or deferred updating of the knowledge base.

Stclair, D. C.↗

NASA NTRS1989

Automation of learning-set testing - The video-task paradigm

Researchers interested in studying discrimination learning in primates have typically utilized variations in the Wisconsin General Test Apparatus (WGTA). In the present experiment, a new testing apparatus for the study of primate learning is proposed. In the video-task paradigm, rhesus monkeys (Macaca mulatta) respond to computer-generated stimuli by manipulating a joystick. Using this apparatus, discrimination learning-set data for 2 monkeys were obtained. Performance on Trial 2 exceeded 80 percent within 200 discrimination learning problems. These data illustrate the utility of the video-task paradigm in comparative research. Additionally, the efficient learning and rich data that were characteristic of this study suggest several advantages of the present testing paradigm over traditional WGTA testing.

Washburn, David A.↗

NASA NTRS1989

Video-task assessment of learning and memory in Macaques (Macaca mulatta) - Effects of stimulus movement on performance

Effects of stimulus movement on learning, transfer, matching, and short-term memory performance were assessed with 2 monkeys using a video-task paradigm in which the animals responded to computer-generated images by manipulating a joystick. Performance on tests of learning set, transfer index, matching to sample, and delayed matching to sample in the video-task paradigm was comparable to that obtained in previous investigations using the Wisconsin General Testing Apparatus. Additionally, learning, transfer, and matching were reliably and significantly better when the stimuli or discriminanda moved than when the stimuli were stationary. External manipulations such as stimulus movement may increase attention to the demands of a task, which in turn should increase the efficiency of learning. These findings have implications for the investigation of learning in other populations, as well as for the application of the video-task paradigm to comparative study.

Washburn, David A.↗

NASA NTRS1992

Learning and tuning fuzzy logic controllers through reinforcements

A new method for learning and tuning a fuzzy logic controller based on reinforcements from a dynamic system is presented. In particular, our Generalized Approximate Reasoning-based Intelligent Control (GARIC) architecture: (1) learns and tunes a fuzzy logic controller even when only weak reinforcements, such as a binary failure signal, is available; (2) introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; (3) introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and (4) learns to produce real-valued control actions. Learning is achieved by integrating fuzzy inference into a feedforward network, which can then adaptively improve performance by using gradient descent methods. We extend the AHC algorithm of Barto, Sutton, and Anderson to include the prior control knowledge of human operators. The GARIC architecture is applied to a cart-pole balancing system and has demonstrated significant improvements in terms of the speed of learning and robustness to changes in the dynamic system's parameters over previous schemes for cart-pole balancing.

Berenji, Hamid R.↗

NASA NTRS1992

A reinforcement learning-based architecture for fuzzy logic control

This paper introduces a new method for learning to refine a rule-based fuzzy logic controller. A reinforcement learning technique is used in conjunction with a multilayer neural network model of a fuzzy controller. The approximate reasoning based intelligent control (ARIC) architecture proposed here learns by updating its prediction of the physical system's behavior and fine tunes a control knowledge base. Its theory is related to Sutton's temporal difference (TD) method. Because ARIC has the advantage of using the control knowledge of an experienced operator and fine tuning it through the process of learning, it learns faster than systems that train networks from scratch. The approach is applied to a cart-pole balancing system.

Berenji, Hamid R.↗

NASA NTRS1993

Structure identification in fuzzy inference using reinforcement learning

In our previous work on the GARIC architecture, we have shown that the system can start with surface structure of the knowledge base (i.e., the linguistic expression of the rules) and learn the deep structure (i.e., the fuzzy membership functions of the labels used in the rules) by using reinforcement learning. Assuming the surface structure, GARIC refines the fuzzy membership functions used in the consequents of the rules using a gradient descent procedure. This hybrid fuzzy logic and reinforcement learning approach can learn to balance a cart-pole system and to backup a truck to its docking location after a few trials. In this paper, we discuss how to do structure identification using reinforcement learning in fuzzy inference systems. This involves identifying both surface as well as deep structure of the knowledge base. The term set of fuzzy linguistic labels used in describing the values of each control variable must be derived. In this process, splitting a label refers to creating new labels which are more granular than the original label and merging two labels creates a more general label. Splitting and merging of labels directly transform the structure of the action selection network used in GARIC by increasing or decreasing the number of hidden layer nodes.

Berenji, Hamid R.↗

NASA NTRS1992

Application of fuzzy logic-neural network based reinforcement learning to proximity and docking operations: Translational controller results

The reinforcement learning techniques developed at Ames Research Center are being applied to proximity and docking operations using the Shuttle and Solar Maximum Mission (SMM) satellite simulation. In utilizing these fuzzy learning techniques, we also use the Approximate Reasoning based Intelligent Control (ARIC) architecture, and so we use two terms interchangeable to imply the same. This activity is carried out in the Software Technology Laboratory utilizing the Orbital Operations Simulator (OOS). This report is the deliverable D3 in our project activity and provides the test results of the fuzzy learning translational controller. This report is organized in six sections. Based on our experience and analysis with the attitude controller, we have modified the basic configuration of the reinforcement learning algorithm in ARIC as described in section 2. The shuttle translational controller and its implementation in fuzzy learning architecture is described in section 3. Two test cases that we have performed are described in section 4. Our results and conclusions are discussed in section 5, and section 6 provides future plans and summary for the project.

Jani, Yashvant↗

NASA NTRS1992

A self-learning rule base for command following in dynamical systems

In this paper, a self-learning Rule Base for command following in dynamical systems is presented. The learning is accomplished though reinforcement learning using an associative memory called SAM. The main advantage of SAM is that it is a function approximator with explicit storage of training samples. A learning algorithm patterned after the dynamic programming is proposed. Two artificially created, unstable dynamical systems are used for testing, and the Rule Base was used to generate a feedback control to improve the command following ability of the otherwise uncontrolled systems. The numerical results are very encouraging. The controlled systems exhibit a more stable behavior and a better capability to follow reference commands. The rules resulting from the reinforcement learning are explicitly stored and they can be modified or augmented by human experts. Due to overlapping storage scheme of SAM, the stored rules are similar to fuzzy rules.

Tsai, Wei K.↗

NASA NTRS1992

Fuzzy learning under and about an unfamiliar fuzzy teacher

This study addresses the problem of optimal parametric learning in unfamiliar fuzzy environments. Prior studies in the domain of unfamiliar environments, which employed either crisp or fuzzy approaches to model the uncertainty or imperfectness of the learning environment, assumed that the training sample labels provided by the unfamiliar teacher were crisp, even if not perfect. Here, the more realistic problem of fuzzy learning under an unfamiliar teacher who provides only fuzzy (instead of crisp) labels, is tackled by expanding the previously defined fuzzy membership concepts to include an additional component representative of the fuzziness of the teacher. The previously studied scenarios, namely, crisp and fuzzy learning under (crisp) unfamiliar teacher, can be looked upon as special cases of this new methodology. As under the earlier studies, the estimated membership functions can then be deployed during the ensuing classification decision phase to judiciously take into account the imperfectness of the learning environment. The study also offers some insight into the properties of several of these fuzzy membership function estimators by examining their behavior under certain specific scenarios.

Dasarathy, Belur V.↗

NASA NTRS1991

On the integration of reinforcement learning and approximate reasoning for control

The author discusses the importance of strengthening the knowledge representation characteristic of reinforcement learning techniques using methods such as approximate reasoning. The ARIC (approximate reasoning-based intelligent control) architecture is an example of such a hybrid approach in which the fuzzy control rules are modified (fine-tuned) using reinforcement learning. ARIC also demonstrates that it is possible to start with an approximately correct control knowledge base and learn to refine this knowledge through further experience. On the other hand, techniques such as the TD (temporal difference) algorithm and Q-learning establish stronger theoretical foundations for their use in adaptive control and also in stability analysis of hybrid reinforcement learning and approximate reasoning-based controllers.

Berenji, Hamid R.↗

NASA NTRS1992

Learning and tuning fuzzy logic controllers through reinforcements

This paper presents a new method for learning and tuning a fuzzy logic controller based on reinforcements from a dynamic system. In particular, our generalized approximate reasoning-based intelligent control (GARIC) architecture (1) learns and tunes a fuzzy logic controller even when only weak reinforcement, such as a binary failure signal, is available; (2) introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; (3) introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and (4) learns to produce real-valued control actions. Learning is achieved by integrating fuzzy inference into a feedforward neural network, which can then adaptively improve performance by using gradient descent methods. We extend the AHC algorithm of Barto et al. (1983) to include the prior control knowledge of human operators. The GARIC architecture is applied to a cart-pole balancing system and demonstrates significant improvements in terms of the speed of learning and robustness to changes in the dynamic system's parameters over previous schemes for cart-pole balancing.

Berenji, Hamid R.↗

NASA NTRS1994

Finding accurate frontiers: A knowledge-intensive approach to relational learning

An approach to analytic learning is described that searches for accurate entailments of a Horn Clause domain theory. A hill-climbing search, guided by an information based evaluation function, is performed by applying a set of operators that derive frontiers from domain theories. The analytic learning system is one component of a multi-strategy relational learning system. We compare the accuracy of concepts learned with this analytic strategy to concepts learned with an analytic strategy that operationalizes the domain theory.

Pazzani, Michael↗

NASA NTRS1995

Locomotion training of legged robots using hybrid machine learning techniques

In this study artificial neural networks and fuzzy logic are used to control the jumping behavior of a three-link uniped robot. The biped locomotion control problem is an increment of the uniped locomotion control. Study of legged locomotion dynamics indicates that a hierarchical controller is required to control the behavior of a legged robot. A structured control strategy is suggested which includes navigator, motion planner, biped coordinator and uniped controllers. A three-link uniped robot simulation is developed to be used as the plant. Neurocontrollers were trained both online and offline. In the case of on-line training, a reinforcement learning technique was used to train the neurocontroller to make the robot jump to a specified height. After several hundred iterations of training, the plant output achieved an accuracy of 7.4%. However, when jump distance and body angular momentum were also included in the control objectives, training time became impractically long. In the case of off-line training, a three-layered backpropagation (BP) network was first used with three inputs, three outputs and 15 to 40 hidden nodes. Pre-generated data were presented to the network with a learning rate as low as 0.003 in order to reach convergence. The low learning rate required for convergence resulted in a very slow training process which took weeks to learn 460 examples. After training, performance of the neurocontroller was rather poor. Consequently, the BP network was replaced by a Cerebeller Model Articulation Controller (CMAC) network. Subsequent experiments described in this document show that the CMAC network is more suitable to the solution of uniped locomotion control problems in terms of both learning efficiency and performance. A new approach is introduced in this report, viz., a self-organizing multiagent cerebeller model for fuzzy-neural control of uniped locomotion is suggested to improve training efficiency. This is currently being evaluated for a possible patent by NASA, Johnson Space Center. An alternative modular approach is also developed which uses separate controllers for each stage of the running stride. A self-organizing fuzzy-neural controller controls the height, distance and angular momentum of the stride. A CMAC-based controller controls the movement of the leg from the time the foot leaves the ground to the time of landing. Because the leg joints are controlled at each time step during flight, movement is smooth and obstacles can be avoided. Initial results indicate that this approach can yield fast, accurate results.

Simon, William E.↗

NASA NTRS1992

There is No Free Lunch: Tradeoffs in the Utility of Learned Knowledge

With the recent introduction of learning in integrated systems, there is a need to measure the utility of learned knowledge for these more complex systems. A difficulty arrises when there are multiple, possibly conflicting, utility metrics to be measured. In this paper, we present schemes which trade off conflicting utility metrics in order to achieve some global performance objectives. In particular, we present a case study of a multi-strategy machine learning system, mutual theory refinement, which refines world models for an integrated reactive system, the Entropy Reduction Engine. We provide experimental results on the utility of learned knowledge in two conflicting metrics - improved accuracy and degraded efficiency. We then demonstrate two ways to trade off these metrics. In each, some learned knowledge is either approximated or dynamically 'forgotten' so as to improve efficiency while degrading accuracy only slightly.

Kedar, Smadar T.↗