Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning algorithms”

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
NASA NTRS1997

Application of Domain Knowledge to Software Quality Assurance

This work focused on capturing, using, and evolving a qualitative decision support structure across the life cycle of a project. The particular application of this study was towards business process reengineering and the representation of the business process in a set of Business Rules (BR). In this work, we defined a decision model which captured the qualitative decision deliberation process. It represented arguments both for and against proposed alternatives to a problem. It was felt that the subjective nature of many critical business policy decisions required a qualitative modeling approach similar to that of Lee and Mylopoulos. While previous work was limited almost exclusively to the decision capture phase, which occurs early in the project life cycle, we investigated the use of such a model during the later stages as well. One of our significant developments was the use of the decision model during the operational phase of a project. By operational phase, we mean the phase in which the system or set of policies which were earlier decided are deployed and put into practice. By making the decision model available to operational decision makers, they would have access to the arguments pro and con for a variety of actions and can thus make a more informed decision which balances the often conflicting criteria by which the value of action is measured. We also developed the concept of a 'monitored decision' in which metrics of performance were identified during the decision making process and used to evaluate the quality of that decision. It is important to monitor those decision which seem at highest risk of not meeting their stated objectives. Operational decisions are also potentially high risk decisions. Finally, we investigated the use of performance metrics for monitored decisions and audit logs of operational decisions in order to feed an evolutionary phase of the the life cycle. During evolution, decisions are revisisted, assumptions verified or refuted, and possible reassessments resulting in new policy are made. In this regard we implemented a machine learning algorithm which automatically defined business rules based on expert assessment of the quality of operational decisions as recorded during deployment.

Wild, Christian W.↗
NASA NTRS1996

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↗
NASA NTRS1994

Toward Real Time Neural Net Flight Controllers

NASA Ames Research Center has an ongoing program in neural network control technology targeted toward real time flight demonstrations using a modified F-15 which permits direct inner loop control of actuators, rapid switching between alternative control designs, and substitutable processors. An important part of this program is the ACTIVE flight project which is examining the feasibility of using neural networks in the design, control, and system identification of new aircraft prototypes. This paper discusses two research applications initiated with this objective in mind: utilization of neural networks for wind tunnel aircraft model identification and rapid learning algorithms for on line reconfiguration and control. The first application involves the identification of aerodynamic flight characteristics from analysis of wind tunnel test data. This identification is important in the early stages of aircraft design because complete specification of control architecture's may not be possible even though concept models at varying scales are available for aerodynamic wind tunnel testing. Testing of this type is often a long and expensive process involving measurement of aircraft lift, drag, and moment of inertia at varying angles of attack and control surface configurations. This information in turn can be used in the design of the flight control systems by applying the derived lookup tables to generate piece wise linearized controllers. Thus, reduced costs in tunnel test times and the rapid transfer of wind tunnel insights into prototype controllers becomes an important factor in more efficient generation and testing of new flight systems. NASA Ames Research Center is successfully applying modular neural networks as one way of anticipating small scale aircraft model performances prior to testing, thus reducing the number of in tunnel test hours and potentially, the number of intermediate scaled models required for estimation of surface flow effects.

Jorgensen, C. C.↗
NASA NTRS1994

Representing Learning With Graphical Models

Probabilistic graphical models are being used widely in artificial intelligence, for instance, in diagnosis and expert systems, as a unified qualitative and quantitative framework for representing and reasoning with probabilities and independencies. Their development and use spans several fields including artificial intelligence, decision theory and statistics, and provides an important bridge between these communities. This paper shows by way of example that these models can be extended to machine learning, neural networks and knowledge discovery by representing the notion of a sample on the graphical model. Not only does this allow a flexible variety of learning problems to be represented, it also provides the means for representing the goal of learning and opens the way for the automatic development of learning algorithms from specifications.

Buntine, Wray L.↗
NASA NTRS2002

Boosting with Averaged Weight Vectors

AdaBoost is a well-known ensemble learning algorithm that constructs its constituent or base models in sequence. A key step in AdaBoost is constructing a distribution over the training examples to create each base model. This distribution, represented as a vector, is constructed to be orthogonal to the vector of mistakes made by the previous base model in the sequence. The idea is to make the next base model's errors uncorrelated with those of the previous model. Some researchers have pointed out the intuition that it is probably better to construct a distribution that is orthogonal to the mistake vectors of all the previous base models, but that this is not always possible. We present an algorithm that attempts to come as close as possible to this goal in an efficient manner. We present experimental results demonstrating significant improvement over AdaBoost and the Totally Corrective boosting algorithm, which also attempts to satisfy this goal.

Oza, Nikunj C.↗
NASA NTRS2002

Visual Inference Programming

The goal of visual inference programming is to develop a software framework data analysis and to provide machine learning algorithms for inter-active data exploration and visualization. The topics include: 1) Intelligent Data Understanding (IDU) framework; 2) Challenge problems; 3) What's new here; 4) Framework features; 5) Wiring diagram; 6) Generated script; 7) Results of script; 8) Initial algorithms; 9) Independent Component Analysis for instrument diagnosis; 10) Output sensory mapping virtual joystick; 11) Output sensory mapping typing; 12) Closed-loop feedback mu-rhythm control; 13) Closed-loop training; 14) Data sources; and 15) Algorithms. This paper is in viewgraph form.

Wheeler, Kevin↗
NASA NTRS2002

Learning Assumptions for Compositional Verification

Compositional verification is a promising approach to addressing the state explosion problem associated with model checking. One compositional technique advocates proving properties of a system by checking properties of its components in an assume-guarantee style. However, the application of this technique is difficult because it involves non-trivial human input. This paper presents a novel framework for performing assume-guarantee reasoning in an incremental and fully automated fashion. To check a component against a property, our approach generates assumptions that the environment needs to satisfy for the property to hold. These assumptions are then discharged on the rest of the system. Assumptions are computed by a learning algorithm. They are initially approximate, but become gradually more precise by means of counterexamples obtained by model checking the component and its environment, alternately. This iterative process may at any stage conclude that the property is either true or false in the system. We have implemented our approach in the LTSA tool and applied it to the analysis of a NASA system.

Cobleigh, Jamieson M.↗
NASA NTRS2004

Product Distribution Theory for Control of Multi-Agent Systems

Product Distribution (PD) theory is a new framework for controlling Multi-Agent Systems (MAS's). First we review one motivation of PD theory, as the information-theoretic extension of conventional full-rationality game theory to the case of bounded rational agents. In this extension the equilibrium of the game is the optimizer of a Lagrangian of the (probability distribution of) the joint stare of the agents. Accordingly we can consider a team game in which the shared utility is a performance measure of the behavior of the MAS. For such a scenario the game is at equilibrium - the Lagrangian is optimized - when the joint distribution of the agents optimizes the system's expected performance. One common way to find that equilibrium is to have each agent run a reinforcement learning algorithm. Here we investigate the alternative of exploiting PD theory to run gradient descent on the Lagrangian. We present computer experiments validating some of the predictions of PD theory for how best to do that gradient descent. We also demonstrate how PD theory can improve performance even when we are not allowed to rerun the MAS from different initial conditions, a requirement implicit in some previous work.

Lee, Chia Fan↗
NASA NTRS2004

Coordination in Large Collectives

Finding the subset of a set of imperfect devices (e.g., nano or micro devices) that results in the best aggregate device is a challenging problem. It is an abstraction of what will likely be a major difficulty in designing and controlling systems of nano or micro-scale components, particularly when a large fraction of those components may be unreliable. Rather than approaching this as a passive search problem, we transform the problem into one of coordination in a complex system by imbuing each device with simple decision making ability. In doing so we face the challenge of determining what each component should attempt to do so that the collective behavior solves the overall problem. Furthermore, in this padicular instance, we face problems of scaling (number of components in the thousands to tens of thousands), observability (components have limited sensing capabilities), and reliability (the components are faulty). We present an approach based on deriving component goals that are aligned with the overall system goal (e.g., forming best aggregate device), and can be computed using information readily (e.g., locally) available to the components. Then, each component in such a collective uses a simple reinforcement learning algorithm to selfishly pursue its own goals. Because those goals are derived in a principled manner, there is no need to use external mechanisms to force collaboration or coordination among the components to ensure that the system reaches a globally desirable solution. The results show that not only this approach provides improvements of over an order of magnitude over both traditional search methods and traditional multi-agent methods, but that the gains increase with the size of the system. This latter result makes this method ideal for domains where the number of components is currently in the thousands and will reach millions in the near future.

Tumer, Kagan↗
NASA NTRS1998

Neural Network Control of a Magnetically Suspended Rotor System

Magnetic bearings offer significant advantages because they do not come into contact with other parts during operation, which can reduce maintenance. Higher speeds, no friction, no lubrication, weight reduction, precise position control, and active damping make them far superior to conventional contact bearings. However, there are technical barriers that limit the application of this technology in industry. One of them is the need for a nonlinear controller that can overcome the system nonlinearity and uncertainty inherent in magnetic bearings. At the NASA Lewis Research Center, a neural network was selected as a nonlinear controller because it generates a neural model without any detailed information regarding the internal working of the magnetic bearing system. It can be used even for systems that are too complex for an accurate system model to be derived. A feed-forward architecture with a back-propagation learning algorithm was selected because of its proven performance, accuracy, and relatively easy implementation.

Choi, Benjamin B.↗
NASA NTRS2005

Designing Agent Utilities for Coordinated, Scalable and Robust Multi-Agent Systems

Coordinating the behavior of a large number of agents to achieve a system level goal poses unique design challenges. In particular, problems of scaling (number of agents in the thousands to tens of thousands), observability (agents have limited sensing capabilities), and robustness (the agents are unreliable) make it impossible to simply apply methods developed for small multi-agent systems composed of reliable agents. To address these problems, we present an approach based on deriving agent goals that are aligned with the overall system goal, and can be computed using information readily available to the agents. Then, each agent uses a simple reinforcement learning algorithm to pursue its own goals. Because of the way in which those goals are derived, there is no need to use difficult to scale external mechanisms to force collaboration or coordination among the agents, or to ensure that agents actively attempt to appropriate the tasks of agents that suffered failures. To present these results in a concrete setting, we focus on the problem of finding the sub-set of a set of imperfect devices that results in the best aggregate device. This is a large distributed agent coordination problem where each agent (e.g., device) needs to determine whether to be part of the aggregate device. Our results show that the approach proposed in this work provides improvements of over an order of magnitude over both traditional search methods and traditional multi-agent methods. Furthermore, the results show that even in extreme cases of agent failures (i.e., half the agents failed midway through the simulation) the system's performance degrades gracefully and still outperforms a failure-free and centralized search algorithm. The results also show that the gains increase as the size of the system (e.g., number of agents) increases. This latter result is particularly encouraging and suggests that this method is ideally suited for domains where the number of agents is currently in the thousands and will reach tens or hundreds of thousands in the near future.

Tumer, Kagan↗
NASA NTRS2004

Abstraction and Assume-Guarantee Reasoning for Automated Software Verification

Compositional verification and abstraction are the key techniques to address the state explosion problem associated with model checking of concurrent software. A promising compositional approach is to prove properties of a system by checking properties of its components in an assume-guarantee style. This article proposes a framework for performing abstraction and assume-guarantee reasoning of concurrent C code in an incremental and fully automated fashion. The framework uses predicate abstraction to extract and refine finite state models of software and it uses an automata learning algorithm to incrementally construct assumptions for the compositional verification of the abstract models. The framework can be instantiated with different assume-guarantee rules. We have implemented our approach in the COMFORT reasoning framework and we show how COMFORT out-performs several previous software model checking approaches when checking safety properties of non-trivial concurrent programs.

Chaki, S.↗
NASA NTRS2004

Support vector machines

Support Vector Machines (SVMs) are a type of supervised learning algorith,, other examples of which are Artificial Neural Networks (ANNs), Decision Trees, and Naive Bayesian Classifiers. Supervised learning algorithms are used to classify objects labled by a 'supervisor' - typically a human 'expert.'.

multiangle↗
NASA NTRS2006

Robust Bioinformatics Recognition with VLSI Biochip Microsystem

A microsystem architecture for real-time, on-site, robust bioinformatic patterns recognition and analysis has been proposed. This system is compatible with on-chip DNA analysis means such as polymerase chain reaction (PCR)amplification. A corresponding novel artificial neural network (ANN) learning algorithm using new sigmoid-logarithmic transfer function based on error backpropagation (EBP) algorithm is invented. Our results show the trained new ANN can recognize low fluorescence patterns better than the conventional sigmoidal ANN does. A differential logarithmic imaging chip is designed for calculating logarithm of relative intensities of fluorescence signals. The single-rail logarithmic circuit and a prototype ANN chip are designed, fabricated and characterized.

bioinformatics↗
NASA NTRS2008

Sensing a Changing Chemical Mixture Using an Electronic Nose

A method of using an electronic nose to detect an airborne mixture of known chemical compounds and measure the temporally varying concentrations of the individual compounds is undergoing development. In a typical intended application, the method would be used to monitor the air in an inhabited space (e.g., the interior of a building) for the release of solvents, toxic fumes, and other compounds that are regarded as contaminants. At the present state of development, the method affords a capability for identifying and quantitating one or two compounds that are members of a set of some number (typically of the order of a dozen) known compounds. In principle, the method could be extended to enable monitoring of more than two compounds. An electronic nose consists of an array of sensors, typically made from polymer carbon composites, the electrical resistances of which change upon exposure to a variety of chemicals. By design, each sensor is unique in its responses to these chemicals: some or all of the sensitivities of a given sensor to the various vapors differ from the corresponding sensitivities of other sensors. In general, the responses of the sensors are nonlinear functions of the concentrations of the chemicals. Hence, mathematically, the monitoring problem is to solve the set of time-dependent nonlinear equations for the sensor responses to obtain the time dependent concentrations of individual compounds. In the present developmental method, successive approximations of the solution are generated by a learning algorithm based on independent-component analysis (ICA) an established information theoretic approach for transforming a vector of observed interdependent signals into a set of signals that are as nearly statistically independent as possible.

Duong, Tuan↗
NASA NTRS2009

Understanding the Scalability of Bayesian Network Inference using Clique Tree Growth Curves

Bayesian networks (BNs) are used to represent and efficiently compute with multi-variate probability distributions in a wide range of disciplines. One of the main approaches to perform computation in BNs is clique tree clustering and propagation. In this approach, BN computation consists of propagation in a clique tree compiled from a Bayesian network. There is a lack of understanding of how clique tree computation time, and BN computation time in more general, depends on variations in BN size and structure. On the one hand, complexity results tell us that many interesting BN queries are NP-hard or worse to answer, and it is not hard to find application BNs where the clique tree approach in practice cannot be used. On the other hand, it is well-known that tree-structured BNs can be used to answer probabilistic queries in polynomial time. In this article, we develop an approach to characterizing clique tree growth as a function of parameters that can be computed in polynomial time from BNs, specifically: (i) the ratio of the number of a BN's non-root nodes to the number of root nodes, or (ii) the expected number of moral edges in their moral graphs. Our approach is based on combining analytical and experimental results. Analytically, we partition the set of cliques in a clique tree into different sets, and introduce a growth curve for each set. For the special case of bipartite BNs, we consequently have two growth curves, a mixed clique growth curve and a root clique growth curve. In experiments, we systematically increase the degree of the root nodes in bipartite Bayesian networks, and find that root clique growth is well-approximated by Gompertz growth curves. It is believed that this research improves the understanding of the scaling behavior of clique tree clustering, provides a foundation for benchmarking and developing improved BN inference and machine learning algorithms, and presents an aid for analytical trade-off studies of clique tree clustering using growth curves.

Mengshoel, Ole Jakob↗
NASA NTRS2009

Finite-difference simulation and visualization of elastodynamics in time-evolving generalized curvilinear coordinates

Modeling and simulation of free and forced structural vibrations is essential to an overall structural health monitoring capability. In the various embodiments, a first principles finite-difference approach is adopted in modeling a structural subsystem such as a mechanical gear by solving elastodynamic equations in generalized curvilinear coordinates. Such a capability to generate a dynamic structural response is widely applicable in a variety of structural health monitoring systems. This capability (1) will lead to an understanding of the dynamic behavior of a structural system and hence its improved design, (2) will generate a sufficiently large space of normal and damage solutions that can be used by machine learning algorithms to detect anomalous system behavior and achieve a system design optimization and (3) will lead to an optimal sensor placement strategy, based on the identification of local stress maxima all over the domain.

Kaul, Upender K.↗
NASA NTRS2010

Automated Assume-Guarantee Reasoning for Omega-Regular Systems and Specifications

We develop a learning-based automated Assume-Guarantee (AG) reasoning framework for verifying omega-regular properties of concurrent systems. We study the applicability of non-circular (AGNC) and circular (AG-C) AG proof rules in the context of systems with infinite behaviors. In particular, we show that AG-NC is incomplete when assumptions are restricted to strictly infinite behaviors, while AG-C remains complete. We present a general formalization, called LAG, of the learning based automated AG paradigm. We show how existing approaches for automated AG reasoning are special instances of LAG.We develop two learning algorithms for a class of systems, called infinite regular systems, that combine finite and infinite behaviors. We show that for infinity-regular systems, both AG-NC and AG-C are sound and complete. Finally, we show how to instantiate LAG to do automated AG reasoning for infinite regular, and omega-regular, systems using both AG-NC and AG-C as proof rules

Chaki, Sagar↗