Institute for Systems Research Technical Reports
Permanent URI for this collectionhttp://hdl.handle.net/1903/4376
This archive contains a collection of reports generated by the faculty and students of the Institute for Systems Research (ISR), a permanent, interdisciplinary research unit in the A. James Clark School of Engineering at the University of Maryland. ISR-based projects are conducted through partnerships with industry and government, bringing together faculty and students from multiple academic departments and colleges across the university.
Browse
32 results
Search Results
Item Statistical Parameter Learning for Belief Networks with Fixed Structure(1999) Li, Hongjun; Baras, John S.; ISR; CSHCNIn this report, we address the problem of parameter learning for belief networks with fixed structure based on empirical observations. Both complete and incomplete (data) observations are included. Given complete data, we describe the simple problem of single parameter learning for intuition and then expand to belief networks under appropriate system decomposition. If the observations are incomplete, we first estimate the "missing" observations and treat them as though they are "real" observations, based on which the parameter learning can be executed as in complete data case. We derive a uniform algorithm based on this idea for incomplete data case and present the convergence and optimality properties. Such an algorithm is suitable trivially under complete observations.Item An Introduction to Belief Networks(1999) Li, Hongjun; Baras, John S.; ISR; CSHCNBelief networks, also called Bayesian networks or probabilistic causal networks, were developed in the late 1970s to model the distributed processing in reading comprehension. Since then they have attracted much attention and have become popular within the AI probability and uncertainty community. As a natural and efficient model for humans' inferential reasoning, belief networks have emerged as the general knowledge representation scheme under uncertainty.In this report, we first introduce belief networks in the light of knowledge representation under uncertainty, then in the remainingsections we give the descriptions of the semantics, inference mechanisms and some issues related to learning belief networks, respectively. This report is not intended to be a tutorial for beginners. Rather it aims to point out some important aspects of belief networks and summarize some important algorithms.
Item An Automated, Distributed, Intelligent Fault Management System for Communication Networks(1999) Li, Hongjun; Baras, John S.; Mykoniatis, George; ISR; CSHCNIn this paper we present a Distributed Intelligent Fault Management (DIFM) system for communication networks. The overall architecture of the proposed system is based on a distributed, cooperative, multi-agent paradigm, with probabilistic networks as the framework for knowledge representation and evidence inferencing. We adopt the management by delegation paradigm for network monitoring and integrate both hard and soft faults.Item REU Report: Development of a Global Information Exchange Database System for the Machinability Evaluation of Dental Ceramics(1999) Katoh, Hironobu; Chen, Bing; Zhang, Guangming; Zhang, Guangming; ISRAesthetic character, high strength, chemical durability, and bio-compatibility make dental ceramics ideal ingredients for fabricatingdental restoratives. However, the inherent brittleness of ceramics poses a challenge to the machining of ceramic restoratives. With the introduction of Dental CAD/CAM system, machinability evaluation is necessary to successfully fabricate dental ceramics for commercial use.This paper presents a unique approach to conduct the systematic experimental research for the machinability of dental ceramics. A database management system is employed to perform the systematic data management and manipulation function. This database engine is then connected to the World Wide Web to take advantage of the information infrastructure provided by it.
Through user-friendly interface, this online database system provides guidance for the experiment design, data collection and data analysis. With the connection of the database to the World Wide Web, interactive web page can be generated to facilitate the information exchange and dissemination. This method utilizes new technologies to allow users to swiftly share information with anyone around the world.
Item REU Report: Process Integration with Wafer Yield: An Exercise in Computer-Based Modules(1999) Park, SunJun; Rubloff, Gary W.; ISRThis report explains the development of the new Wafer Yield simulation.It shows the user the various effects of numerous factors in manufacturingon total yield, the algorithms behind it, an explanation of the OLE systemthat allows the transfers to occur, the reasoning behind the selectedmeans of presenting the data, and future directions of the project.Item Integrated, Distributed Fault Management for Communication Networks(1998) Baras, John S.; Li, Hongjun; Mykoniatis, G.; Baras, John S.; ISR; CSHCNThis report describes an integrated, distributed fault management (IDFM) system for communication networks. The architecture is based on a distributed intelligent agent paradigm, with probabilistic networks as the framework for knowledge representation and evidence inferencing. A static strategy for generating the suggestive test sequence is proposed, based on which a heuristic dynamic strategy is initiated. Another dynamic strategy, formulated as a Markov decision problem, is also provided. To solve this problem, reinforcement learning techniques are investigated.Item Advances in High Performance Knowledge Representation(1996) Stoffel, K.; Taylor, M.; Hendler, James A.; Saltz, J.; Andersen, William; ISRReal world applications are demanding that KR systems provide support for knowledge bases containing millions of assertions. We present Parka-DB, a high-performance reimplementation of the Parka KR language which uses a standard relational DBMS. The integration of a DBMS and the Parka KR language allows us to efficiently support complex queries on extremely large KBs using a single processor, as opposed to our earlier massively parallel system. In addition, the system can make good use of secondary memory, with the whole system needing less than 16MB of RAM to hold a KB of over 2,000,000 assertions. We demonstrate empirically that this reduction in primary storage requires only about 10% overhead in time, and decreases the load time of very large KBs by more than two orders of magnitude.Item Dynamic Attractors and Basin Class Capacity in Binary Neural Networks(1995) Dayhoff, Judith E.; Palmadesso, Peter J.; ISRThe wide repertoire of attractors and basins of attraction that appear in dynamic neural networks not only serve as models of brain activity patterns but create possibilities for new computational paradigms that use attractors and their basins. To develop such computational paradigms, it is first critical to assess neural network capacity for attractors and for differing basins of attraction, depending on the number of neurons and the weights. In this paper we analyze the attractors and basins of attraction for recurrent, fully-connected single layer binary networks. We utilize the network transition graph - a graph that shows all transitions from one state to another for a given neural network - to show all oscillations and fixed-point attractors, along with the basins of attraction. Conditions are shown whereby pairs of transitions are possible from the same neural network. We derive a lower bound for the number of transition graphs possible 2n2- n , for an n-neuron network. Simulation results show a wide variety of transition graphs and basins of attraction and sometimes networks have more attractors than neurons. We count thousands of basin classes - networks with differing basins of attraction - in networks with as few as five neurons. Dynamic networks show promise for overcoming the limitations of static neural networks, by use of dynamic attractors and their basins. We show that dynamic networks have high capacity for basin classes, can have more attractors than neurons, and have more stable basin boundaries than in the Hopfield associative memory.Item Using the Parka Parallel Knowledge Representation System (Version 3.2)(1995) Kettler, Brian; Andersen, William; Hendler, James A.; Luke, Sean; ISRParka is a symbolic, semantic network knowledge representation system that takes advantage of the massive parallelism of supercomputers such as the Connection Machine. The Parka language has many of the features of traditional semantic net/frame-based knowledge representation languages but also supports several kinds of rapid parallel inference mechanisms that scale to large knowledge-bases of hundreds of thousands of frames or more. Parka is intended for general-purpose use and has been used thus far to support, A.I. systems for case-based reasoning and data mining.This document is a user manual for the current version of Parka, version 3.2. It describes the Parka language and presents some examples of knowledge representation using Parka. Details about the parallel algorithms, implementation, and empirical results are presented elsewhere.
Item A Critical Look at Critics in HTN Planning(1995) Erol, Kutluhan; Hendler, James A.; Nau, D.S.; Tsuneto, R.; ISRDetecting interactions and resolving conflicts in one of the key issues for generative planning systems. Hierarchical Task Network (HTN) planning systems use critics for this purpose. Critics have provided extra efficiency and flexibility to HTN planning systems, but their procedural -- and sometimes domain- specific - - nature has not been amenable to analytical studies. As a result, little work is available on the correctness or efficiency of critics. This paper describes a principled approach to handling conflicts, as implemented in UMCP, an HTN planning system. Critics in UMCP have desirable properties such as systematicity, and the preservation of soundness and completeness.