Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “LEARNING SYSTEM”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

Goal Directed Model Inversion: Learning Within Domain Constraints

Goal Directed Model Inversion (GDMI) is an algorithm designed to generalize supervised learning to the case where target outputs are not available to the learning system. The output of the learning system becomes the input to some external device or transformation, and only the output of this device or transformation can be compared to a desired target. The fundamental driving mechanism of GDMI is to learn from success. Given that a wrong outcome is achieved, one notes that the action that produced that outcome "would have been right if the outcome had been the desired one." The algorithm makes use of these intermediate "successes" to achieve the final goal. A unique and potentially very important feature of this algorithm is the ability to modify the output of the learning module to force upon it a desired syntactic structure. This differs from ordinary supervised learning in the following way: in supervised learning the exact desired output pattern must be provided. In GDMI instead, it is possible to require simply that the output obey certain rules, i.e., that it "make sense" in some way determined by the knowledge domain. The exact pattern that will achieve the desired outcome is then found by the system. The ability to impose rules while allowing the system to search for its own answers in the context of neural networks is potentially a major breakthrough in two ways: 1) it may allow the construction of networks that can incorporate immediately some important knowledge, i.e. would not need to learn everything from scratch as normally required at present, and 2) learning and searching would be limited to the areas where it is necessary, thus facilitating and speeding up the process. These points are illustrated with examples from robotic path planning and parametric design.

Colombano, Silvano P.↗
NASA NTRS1994

Goal Directed Model Inversion: Learning Within Domain Constraints

Goal Directed Model Inversion (GDMI) is an algorithm designed to generalize supervised learning to the case where target outputs are not available to the learning system. The output of the learning system becomes the input to some external device or transformation, and only the output of this device or transformation can be compared to a desired target. The fundamental driving mechanism of GDMI is to learn from success. Given that a wrong outcome is achieved, one notes that the action that produced that outcome "would have been right if the outcome had been the desired one." The algorithm makes use of these intermediate "successes" to achieve the final goal. A unique and potentially very important feature of this algorithm is the ability to modify the output of the learning module to force upon it a desired syntactic structure. This differs from ordinary supervised learning in the following way: in supervised learning the exact desired output pattern must be provided. In GDMI instead, it is possible to require simply that the output obey certain rules, i.e., that it "make sense" in some way determined by the knowledge domain. The exact pattern that will achieve the desired outcome is then found by the system. The ability to impose rules while allowing the system to search for its own answers in the context of neural networks is potentially a major breakthrough in two ways: (1) it may allow the construction of networks that can incorporate immediately some important knowledge, i.e., would not need to learn everything from scratch as normally required at present; and (2) learning and searching would be limited to the areas where it is necessary, thus facilitating and speeding up the process. These points are illustrated with examples from robotic path planning and parametric design.

Colombano, Silvano P.↗
NASA NTRSDate not supplied

Interpretable Convolutional Learning Classifier System (C-LCS) for Higher Dimensional Datasets

The purpose of this paper is to devise an interpretable hybrid classification model for Convolutional Neural Networks (CNN) and a Learning Classifier System (LCS). The presented hybrid system integrates the fundamental attributes from both types of these classifiers. In the proposed hybrid model CNN works as an automatic feature extractor, and LCS works to provide interpretable rule-based classification results. Although LCS has limitations working on higher dimensional datasets, we resolve this limitation by using CNN as a feature extractor. The other concept of the non-interpretability of CNN is addressed by using the LCS rule. Furthermore, our experiment with higher dimensional datasets like CIFAR-10 and Fashion-MNIST shows that extended LCS provides comparable performance to the standard neural network model while also providing interpretable results. We named this extended LCS method Convolutional Learning Classifier Cystem (C-LCS).

Jelani Owens↗
NASA NTRS2012

LEGION: Lightweight Expandable Group of Independently Operating Nodes

LEGION is a lightweight C-language software library that enables distributed asynchronous data processing with a loosely coupled set of compute nodes. Loosely coupled means that a node can offer itself in service to a larger task at any time and can withdraw itself from service at any time, provided it is not actively engaged in an assignment. The main program, i.e., the one attempting to solve the larger task, does not need to know up front which nodes will be available, how many nodes will be available, or at what times the nodes will be available, which is normally the case in a "volunteer computing" framework. The LEGION software accomplishes its goals by providing message-based, inter-process communication similar to MPI (message passing interface), but without the tight coupling requirements. The software is lightweight and easy to install as it is written in standard C with no exotic library dependencies. LEGION has been demonstrated in a challenging planetary science application in which a machine learning system is used in closed-loop fashion to efficiently explore the input parameter space of a complex numerical simulation. The machine learning system decides which jobs to run through the simulator; then, through LEGION calls, the system farms those jobs out to a collection of compute nodes, retrieves the job results as they become available, and updates a predictive model of how the simulator maps inputs to outputs. The machine learning system decides which new set of jobs would be most informative to run given the results so far; this basic loop is repeated until sufficient insight into the physical system modeled by the simulator is obtained.

Burl, Michael C.↗
NASA NTRS1996

The micro conical system: Lessons learned from a successful EVA/robot-compatible mechanism

The Micro Conical System (MCS) is a three-part, multi-purpose mechanical interface system used for acquiring and manipulating masses on-orbit by either extravehicular activity (EVA) or telerobotic means. The three components of the system are the micro conical fitting (MCF), the EVA micro tool (EMCT), and the Robot Micro Conical Tool (RMCT). The MCS was developed and refined over a four-year period. This period culminated with the delivery of 358 Class 1 and Class 2 micro conical fittings for the International Space Station and with its first use in space to handle a 1272 kg (2800 lbm) Spartan satellite (11000 times greater than the MCF mass) during an EVA aboard STS-63 in February, 1995. The micro conical system is the first successful EVA/robot-compatible mechanism to be demonstrated in the external environment aboard the U.S. Space Shuttle.

Gittleman, Mark↗
NASA NTRS1992

Techniques for improving transients in learning control systems

A discrete modern control formulation is used to study the nature of the transient behavior of the learning process during repetitions. Several alternative learning control schemes are developed to improve the transient performance. These include a new method using an alternating sign on the learning gain, which is very effective in limiting peak transients and also very useful in multiple-input, multiple-output systems. Other methods include learning at an increasing number of points progressing with time, or an increasing number of points of increasing density.

Chang, C.-K.↗
NASA NTRS2009

MODIS Science Algorithms and Data Systems Lessons Learned

For almost 10 years, standard global products from NASA's Earth Observing System s (EOS) two Moderate Resolution Imaging Spectroradiometer (MODIS) sensors are being used world-wide for earth science research and applications. This paper discusses the lessons learned in developing the science algorithms and the data systems needed to produce these high quality data products for the earth sciences community. Strong science team leadership and communication, an evolvable and scalable data system, and central coordination of QA and validation activities enabled the data system to grow by two orders of magnitude from the initial at-launch system to the current system able to reprocess data from both the Terra and Aqua missions in less than a year. Many of the lessons learned from MODIS are already being applied to follow-on missions.

Wolfe, Robert E.↗
NASA NTRS1991

Intelligent control based on fuzzy logic and neural net theory

In the conception and design of intelligent systems, one promising direction involves the use of fuzzy logic and neural network theory to enhance such systems' capability to learn from experience and adapt to changes in an environment of uncertainty and imprecision. Here, an intelligent control scheme is explored by integrating these multidisciplinary techniques. A self-learning system is proposed as an intelligent controller for dynamical processes, employing a control policy which evolves and improves automatically. One key component of the intelligent system is a fuzzy logic-based system which emulates human decision making behavior. It is shown that the system can solve a fairly difficult control learning problem. Simulation results demonstrate that improved learning performance can be achieved in relation to previously described systems employing bang-bang control. The proposed system is relatively insensitive to variations in the parameters of the system environment.

Lee, Chuen-Chien↗
NASA NTRS1999

Designing Specification Languages for Process Control Systems: Lessons Learned and Steps to the Future

Previously, we defined a blackbox formal system modeling language called RSML (Requirements State Machine Language). The language was developed over several years while specifying the system requirements for a collision avoidance system for commercial passenger aircraft. During the language development, we received continual feedback and evaluation by FAA employees and industry representatives, which helped us to produce a specification language that is easily learned and used by application experts. Since the completion of the PSML project, we have continued our research on specification languages. This research is part of a larger effort to investigate the more general problem of providing tools to assist in developing embedded systems. Our latest experimental toolset is called SpecTRM (Specification Tools and Requirements Methodology), and the formal specification language is SpecTRM-RL (SpecTRM Requirements Language). This paper describes what we have learned from our use of RSML and how those lessons were applied to the design of SpecTRM-RL. We discuss our goals for SpecTRM-RL and the design features that support each of these goals.

Leveson, Nancy G.↗
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 NTRS1994

Customizing the JPL Multimission Ground Data System: Lessons Learned

This paper will describe lessons learned in adapting JPL's Multimission Ground Data System (MGDS) to fly the Voyager, Galileo, and Mars Observer missions. We will explain how powerful, existing ground data systems can be adapted and packaged in a cost effective way for operations of small and large planetary missions. We will also describe how the MGDS was adapted to support operations within the Galileo Spacecraft Testbed. The Galileo testbed provided a unique opportunity to adapt MGDS to support command and control operations for a small autonomous operations team with a handful of engineers flying the Galileo Spacecraft flight system model.

ground↗
NASA NTRSDate not supplied

Problems in Machine Learning-Based Systems for Safety-Critical Avionics

To explore, discover, and understand the impact on safety of growing complexity introduced by modernization aimed at improving the efficiency of flight, the access to airspace, and/or the expansion of services provided by air vehicles. To develop and demonstrate innovative solutions that enable this modernization and the aviation transformation envisioned by ARMD through proactive mitigation of risks in accordance with target levels of safety.

Safety Critical Systems↗
NASA NTRS2018

Toward Justifiable Trust in Autonomous Systems Incorporating Human Knowledge in Autonomous Systems through Machine Learning

Trust in Autonomous Systems is largely about humans trusting the decisions made by autonomous systems. This trust can be increased through learning from domain experts. In particular, autonomous systems can learn offline from past mission operations before conducting any operations of its own. Additionally, autonomous systems can learn online by obtaining human feedback during operations. We will discuss several classes of machine learning methods and our application of them to autonomous systems. The first class of methods is anomaly detection, which uses operations data to identify examples of anomalous operations. The second class of methods is inverse reinforcement learning, also known as apprenticeship learning, that takes past operations data as input and yields a controller that is able to duplicate the operations described by the data. The third class is active learning, which identifies examples on which the model is most uncertain and requests domain expert feedback.

Oza, Nikunj C.↗
NASA NTRS1987

Fallible humans and vulnerable systems - Lessons learned from aviation

It is suggested that the problems being experienced in complex automatic systems are essentially due to the failure of information management and communication. The failure covers the entire spectrum: display devices and techniques, coding information so as to reduce human error, and information economy, i.e., resisting the temptation to bombard the operator with unlimited information simply because the system possesses the capability to do so. Since there has been great progress in hardware engineering, it is suggested that further attention is needed in the 'soft' side of systems. The approach should focus on (1) preventing human cognitive slips and (2) making the systems less vulnerable to such slips when they do occur. Most of the examples are taken from studies of cockpit automation.

Wiener, Earl L.↗