In VISION-21 Symposium. NASA Lewis Research Center and the Ohio Aerospace Institute.

Proceedings of the Eleventh National Conference on Artificial Intelligence (AAAI93), American Association for Artificial Intelligence, Washington, DC, July 1993, pp. 392-397.

We describe in this paper a novel application of neural networks to system health monitoring of a large antenna for deep space communications. The paper outlines our approach to building a monitoring system using hybrid signal processing and neural network techniques, including autoregressive modelling, pattern recognition, and Hidden Markov models. We discuss several problems which are somewhat generic in applications of this kind - in particular we address the problem of detecting classes which were not present in the training data. Experimental results indicate that the proposed system is sufficiently reliable for practical implementation. 1 Background: The Deep Space Network The Deep Space Network (DSN) (designed and operated by the Jet Propulsion Laboratory (JPL) for the National Aeronautics and Space Administration (NASA)) is unique in terms of providing end-to-end telecommunication capabilities between earth and various interplanetary spacecraft throughout the solar system. The ground component of the DSN consists of three ground station complexes located in California, Spain and Australia, giving full 24-hour coverage for deep space communications.

An important issue in neural computation is the dynamic range of weights in the neural networks. Many experimental results on learning indicate that the weights in the networks can grow prohibitively large with the size of the inputs. Here we address this issue by studying the tradeoffs between the depth and the size of weights in polynomial-size networks of linear threshold elements (LTEs). We show that there is an efficient way of simulating a network of LTEs with large weights by a network of LTEs with small weights. To prove these results, we use tools from harmonic analysis of Boolean functions.

Padhraic Smyth, J eft" Mellstrom Jet Propulsion Laboratory 238-420 California Institute of Technology Pasadena, CA 91109 Abstract We describe in this paper a novel application of neural networks to system health monitoring of a large antenna for deep space communications. The paper outlines our approach to building a monitoring system using hybrid signal processing and neural network techniques, including autoregressive modelling, pattern recognition, and Hidden Markov models. We discuss several problems which are somewhat generic in applications of this kind - in particular we address the problem of detecting classes which were not present in the training data. Experimental results indicate that the proposed system is sufficiently reliable for practical implementation. 1 Background: The Deep Space Network The Deep Space Network (DSN) (designed and operated by the Jet Propulsion Laboratory (JPL)for the National Aeronautics and Space Administration (NASA)) is unique in terms of ...

Kai-Yeung Siu Dept. of Electrical & Computer Engineering University of California, Irvine Irvine, CA 92717 Jehoshua Bruck IBM Research Division Almaden Research Center San Jose, CA 95120-6099 Abstract An important issue in neural computation is the dynamic range of weights in the neural networks. Many experimental results on learning indicate that the weights in the networks can grow prohibitively large with the size of the inputs. We show that there is an efficient way of simulating a network of LTEs with large weights by a network of LTEs with small weights. To prove these results, we use tools from harmonic analysis of Boolean functions. Our technique is quite general, it provides insights to some other problems.

We describe in this paper a novel application of neural networks to system health monitoring of a large antenna for deep space communications. The paper outlines our approach to building a monitoring system using hybrid signal processing and neural network techniques, including autoregressive modelling, pattern recognition, and Hidden Markov models. We discuss several problems which are somewhat generic in applications of this kind - in particular we address the problem of detecting classes which were not present in the training data. Experimental results indicate that the proposed system is sufficiently reliable for practical implementation. 1 Background: The Deep Space Network The Deep Space Network (DSN) (designed and operated by the Jet Propulsion Laboratory (JPL) for the National Aeronautics and Space Administration (NASA)) is unique in terms of providing end-to-end telecommunication capabilities between earth and various interplanetary spacecraft throughout the solar system. The ground component of the DSN consists of three ground station complexes located in California, Spain and Australia, giving full 24-hour coverage for deep space communications.

This article is a slightly modified version of an invited address that was given at the Eighth IEEE Conference on Artificial Intelligence for Applications in Monterey, California, on 2 March 1992. It describes the lessons learned in developing and implementing the Artificial Intelligence Research and Development Program at the National Aeronautics and Space Administration (NASA). These stages are similar to the "ages of artificial intelligence" that Pat Winston described a year before the NASA program was initiated. The final section of the article attempts to generalize some of the lessons learned during the first seven years of the NASA AI program into AI program management heuristics.

NASA's AI program has implemented Rather, it is to attempt to describe the lessons learned in the process of putting the program in setting up and carrying out the first together and carrying it out. Research and Development Program at the Did the plan work? How did National Aeronautics and Space Administration the program readjust? This AI program is sponsored by faced, and how would they be handled differently NASA's Office of Aeronautics and Space Technology. What are the heuristics used to The program conducts research and keep NASA's AI ship afloat in the churning development at the NASA centers (Ames, seas of government politics? It team never got lost in the process of setting also sponsors research in academia and industry, up the AI program, there were a few times primarily through Ames Research Center, when it was temporarily directionally disoriented. There were encounters with the NASA. The AI group at Ames, which is headed unforeseen that called for real-time reactive by Peter Friedland, has particular strengths in replanning.

De Kleer agreed Institute for the Learning Sciences, university laboratories to real-world that model construction can be difficult Troy Heindel of the Gensym Corporation development efforts, state-of-the-art but noted that the overhead involved (formerly of NASA Johnson research in model-based reasoning in developing structural, Space Center [JSC]), Ben Kuipers of (MBR), and an overview of relevant functional, or causal models is not the University of Texas at Austin, research and applications activities in worse than that associated with developing Ethan Scarl of Boeing Computing the European Space Agency (ESA).