Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Keyword
-
- Localization (6)
- Information retrieval (4)
- Robotics (4)
- Algorithms (3)
- Reinforcement learning (3)
-
- Cache (2)
- Computer Vision (2)
- Digital elevation models (2)
- Evaluation (2)
- Information Retrieval (2)
- Language Models (2)
- Machine Learning (2)
- Mobile robots (2)
- Photogrammetry (2)
- Probabilistic memory safety (2)
- Simulation (2)
- World Wide Web (2)
- Reinforcement Learning (RL) (1)
- decision-theoretic planning. (1)
- explicit congestion notification (ECN) (1)
- explicit loss notification (ELN) (1)
- notation. (1)
- 3D (1)
- Abstraction (1)
- Alias analysis (1)
- Anomaly detection. (1)
- Anonymity (1)
- Anonymous communication (1)
- Application (1)
- Applications (1)
Articles 211 - 232 of 232
Full-Text Articles in Physical Sciences and Mathematics
Real-Time And Embedded Systems, John A. Stankovic
Real-Time And Embedded Systems, John A. Stankovic
Computer Science Department Faculty Publication Series
No abstract provided.
Indexing Handwriting Using Word Matching, R. Manmatha
Indexing Handwriting Using Word Matching, R. Manmatha
Computer Science Department Faculty Publication Series
There are many historical manuscripts written in a single hand which it would be useful to index. Examples include theW. B. DuBois collection at theUniversity ofMassachusetts and the early Presidential libraries at the Library of Congress. The standard technique for indexing documents is to scan them in, convert them to machine readable form (ASCII) using Optical Character Recognition (OCR) and then index them using a text retrieval engine. However, OCR does not work well on handwriting. Here an alternative scheme is proposed for indexing such texts. Each page of the document is segmented into words. The images of the words …
Improving The Accuracy Of Petri Net-Based Analysis Of Concurrent Programs, A. T. Chamillard, Lori A. Clarke
Improving The Accuracy Of Petri Net-Based Analysis Of Concurrent Programs, A. T. Chamillard, Lori A. Clarke
Computer Science Department Faculty Publication Series
Spurious results are an inherent problem of most static analysis methods. These methods, in an effort to produce conservative results, overestimate the executable behavior of a program. Infeasible paths and imprecise alias resolution are the two causes of such inaccuracies. In this paper we present an approach for improving the accuracy of Petri net-based analysis of concurrent programs by including additional program state information in the Petri net. We present empirical results that demonstrate the improvements in accuracy and, in some cases, the reduction in the search space that result from applying this approach to concurrent Ada programs.
Tracking Object Motion Across Aspect Changes For Augmented Reality, S. Ravela
Tracking Object Motion Across Aspect Changes For Augmented Reality, S. Ravela
Computer Science Department Faculty Publication Series
A model registration system capable of tracking an object through distinct aspects in real-time is presented. The system integrates tracking, pose determination, and aspect graph indexing. The tracking combines steerable filters with normalized cross-correlation, compensates for rotation in 2D and is adaptive. Robust statistical methods are used in the pose estimation to detect and remove mismatches. The aspect graph is used to determine when features will disappear or become difficult to track an dto predict when and where new features will become trackable. The overall system is stable and is amenable to real-time performance.
Learning Situation-Specific Coordination In Generalized Partial Global Planning, M. V. Nagendra Prasad, Victor R. Lesser
Learning Situation-Specific Coordination In Generalized Partial Global Planning, M. V. Nagendra Prasad, Victor R. Lesser
Computer Science Department Faculty Publication Series
No abstract provided.
Execution Performance Issues In Full-Text Information Retrieval, Eric W. Brown
Execution Performance Issues In Full-Text Information Retrieval, Eric W. Brown
Computer Science Department Faculty Publication Series
The task of an information retrieval system is to identify documents that will satisfy a user’s information need. Effective fulfillment of this task has long been an active area of research, leading to sophisticated retrieval models for representing information content in documents and queries and measuring similarity between the two. The maturity and proven effectiveness of these systems has resulted in demand for increased capacity, performance, scalability, and functionality, especially as information retrieval is integrated into more traditional database management environments. In this dissertation we explore a number of functionality and performance issues in information retrieval. First, we consider creation …
Packet Loss Correlation In The Mbone Multicast Network, Maya Yajnik, Jim Kurose, Don Towsley
Packet Loss Correlation In The Mbone Multicast Network, Maya Yajnik, Jim Kurose, Don Towsley
Computer Science Department Faculty Publication Series
The recent success ofmulticast applications such as Internet teleconferencing illustrates the tremendous potential of applications built upon wide-area multicast communication services. A critical issue for such multicast applications and the higher layer protocols required to support them is the manner in which packet losses occur within the multicast network. In this paper we present and analyze packet loss data collected on multicast-capable hosts at 17 geographically distinct locations in Europe and the US and connected via the MBone. We experimentally and quantitatively examine the spatial and temporal correlation in packet loss among participants in a multicast session. Our results show …
Knowledge-Directed Vision: Control, Learning, And Integration, Bruce A. Draper, Allen R. Hanson, Edward M. Riseman
Knowledge-Directed Vision: Control, Learning, And Integration, Bruce A. Draper, Allen R. Hanson, Edward M. Riseman
Computer Science Department Faculty Publication Series
The knowledge-directed approach to image interpretation, popular in the 1980's, sought to identify objects in unconstrained two-dimensional images and to determine the threedimensional relationships between these objects and the camera by applying large amounts of object- and domain-specific knowledge to the interpretation problem. Among the primary issues faced by these systems were variations among instances of an object class and differences in how object classes were defined in terms of shape, color, function, texture, size, and/or substructures. This paper argues that knowledge-directed vision systems typically failed for two reasons. The first is that the low- and mid-level vision procedures that …
Lightweight Write Detection And Checkpointing For Fine-Grained Persistence, Antony L. Hosking, J. Eliot B. Moss
Lightweight Write Detection And Checkpointing For Fine-Grained Persistence, Antony L. Hosking, J. Eliot B. Moss
Computer Science Department Faculty Publication Series
Many systems must dynamically track writes to cached data, for the purpose of reconciling those updates with respect to the permanent or global state of the data. For example, distributed systems employ coherency protocols to ensure a consistent view of shared data. Similarly, database systems log updates both for concurrency control and to ensure the resilience of those updates in the face of system failures. Here, we measure and compare the absolute performance of several alternative mechanisms for the lightweight detection of writes to cached data in a persistent system, and the relative overhead to log those writes to stable …
Large Deviations And The Generalized Processor Sharing Scheduling: Upper And Lower Bounds Part I: Two-Queue Systems, Zhi-Li Zhang
Large Deviations And The Generalized Processor Sharing Scheduling: Upper And Lower Bounds Part I: Two-Queue Systems, Zhi-Li Zhang
Computer Science Department Faculty Publication Series
We prove asymptotic upper and lower bounds on the asymptotic decay rate of per-session queue length tail distributions for a single constant service rate server queue shared by multiple sessions with the generalized processor sharing (GPS) scheduling discipline. The simpler case of a GPS system with only two queues needs special attention, as under this case, it is shown that the upper bounds and lower boundsmatch, thus yielding exact bounds. This result is established in this part (Part I) of the paper. The general case is much more complicated, and is treated separately in Part II of the paper [42], …
Coordination Assistance For Mixed Human And Computational Agent Systems, Keith S. Decker, Victor R. Lesser
Coordination Assistance For Mixed Human And Computational Agent Systems, Keith S. Decker, Victor R. Lesser
Computer Science Department Faculty Publication Series
In many application areas (such as concurrent engineering, software development, hospital scheduling, manufacturing scheduling, and military planning), individuals are responsible for an agenda of tasks and face choices about the best way to locally handle each task, in what order to do tasks, and when to do them. Such decisions are often hard tomake because of coordination problems: individual tasks are related to the tasks of others in complex ways, and there aremany sources of uncertainty (no one has a complete view of the task structure at arbitrary levels of detail, the situationmay be changing dynamically, and no one is …
Crystal: Inducing A Conceptual Dictionary, Stephen Soderland
Crystal: Inducing A Conceptual Dictionary, Stephen Soderland
Computer Science Department Faculty Publication Series
One of the central knowledge sources of an information extraction (IE) system IS a dictionary of linguistic patterns that can be used to identify references to relevant information in a text Automatic creation of conceptual dictionaries is important for portability and scalability of an IE system This paper describes CRYSTAL, a system which automatically induces a dictionary of "concept-node definitions" sufficient to identify relevant information from a training corpus Each of these concept-node definitions is generalized as far as possible without producing errors, so that a minimum number of dictionary entries cover the positive training instances Because it tests the …
Adaptive Critics And The Basal Ganglia, Andrew G. Barto
Adaptive Critics And The Basal Ganglia, Andrew G. Barto
Computer Science Department Faculty Publication Series
No abstract provided.
Approximate Reasoning Using Anytime Algorithms, Shlomo Zilberstein
Approximate Reasoning Using Anytime Algorithms, Shlomo Zilberstein
Computer Science Department Faculty Publication Series
The complexity of reasoning in intelligent systems makes it undesirable, and sometimes infeasible, to find the optimal action in every situation since the deliberation process itself degrades the performance of the system. The problem is then to construct intelligent systems that react to a situation after performing the “right” amount of thinking. It is by now widely accepted that a successful system must trade off decision quality against the computational requirements of decision-making. Anytime algorithms, introduced by Dean, Horvitz and others in the late 1980’s, were designed to offer such a trade-off. We have extended their work to the construction …
Adaptive Tracking And Model Registration Across Distinct Aspects, S. Ravela
Adaptive Tracking And Model Registration Across Distinct Aspects, S. Ravela
Computer Science Department Faculty Publication Series
A model registration system capable of tracking an object through distinct aspects in real-time is presented. The system integrates tracking, pose determination, and aspect graph indexing. The tracking combines steerable filters with normalized cross-correlation, compensates for rotation in 2D and is adaptive. Robust statistical methods are used in the pose estimation to detect and remove mismatches. The aspect graph is used to determine when features will disappear or become difficult to trade and to predict when and where new features will become trackable. The overall system is stable and is amenable to real-time performance.
Connectivity And Performance Tradeoffs In The Cascade Correlation Learning Architecture, D. S. Phatak, I. Koren
Connectivity And Performance Tradeoffs In The Cascade Correlation Learning Architecture, D. S. Phatak, I. Koren
Computer Science Department Faculty Publication Series
The Cascade Correlation [1] is a very flexible, efficient and fast algorithm for supervised learning. It incrementally builds the network by adding hidden units one at a time, until the desired input/output mapping is achieved. It connects all the previously installed units to the new unit being added. Consequently, each new unit in effect adds a new layer and the fan–in of the hidden and output units keeps on increasing as more units get added. The resulting structure could be hard to implement in VLSI, because the connections are irregular and the fan-in is unbounded. Moreover, the depth or the …
Isr3: Communication And Data Storage For An Unmanned Ground Vehicle*, Bruce A. Draper, Gökhan Kutlu, Edward M. Riseman, Allen R. Hanson
Isr3: Communication And Data Storage For An Unmanned Ground Vehicle*, Bruce A. Draper, Gökhan Kutlu, Edward M. Riseman, Allen R. Hanson
Computer Science Department Faculty Publication Series
Computer vision researchers working in mobile robotics and other real-time domains are forced to confront issues not normally addressed in the computer vision literature. Among these are: communications or how to get data from one process to another; data storage and retrieval (primarily for transient image-based data); and database management for maps, object model and other permanent (typically 3D) data. This paper reviews efforts at CMU, SRI and UMass to build real-time computer vision systems for mobile robotics, and presents a new tool, called ISR3, for communications, data storage/retrieval and database management on the UMass Mobile Perception Laboratory (MPL), a …
Domain-Specific Knowledge Acquisition For Conceptual Sentence Analysis, Claire Cardie
Domain-Specific Knowledge Acquisition For Conceptual Sentence Analysis, Claire Cardie
Computer Science Department Faculty Publication Series
The availability of on-line corpora is rapidly changing the field of natural language processing (NLP) from one dominated by theoretical models of often very specific linguistic phenomena to one guided by computational models that simultaneously account for a wide variety of phenomena that occur in real-world text. Thus far, among the best-performing and most robust systems for reading and summarizing large amounts of real-world text are knowledge-based natural language systems. These systems rely heavily on domain-specific, handcrafted knowledge to handle the myriad syntactic, semantic, and pragmatic ambiguities that pervade virtually all aspects of sentence analysis. Not surprisingly, however, generating this …
A Language-Independent Garbage Collector Toolkit, Richard L. Hudson
A Language-Independent Garbage Collector Toolkit, Richard L. Hudson
Computer Science Department Faculty Publication Series
We describe a memory management toolkit for language implementors. It offers efficient and flexible generation scavenging garbage collection. In addition to providing a core of languageindependent algorithms and data structures, the toolkit includes auxiliary components that ease implementation of garbage collection for programming languages. We have detailed designs for Smalltalk and Modula-3 and are confident the toolkit can be used with a wide variety of languages. The toolkit approach is itself novel, and our design includes a number of additional innovations in flexibility, efficiency, accuracy, and cooperation between the compiler and the collector.
Two Kinds Of Training Information For Evaluation Function Learning, Paul Utgoff
Two Kinds Of Training Information For Evaluation Function Learning, Paul Utgoff
Computer Science Department Faculty Publication Series
This paper identifies two fundamentally different kinds of training information for learning search control in terms of an evaluation function. Each kind of training information suggests its own set of methods for learning an evaluation function. The paper shows that one can integrate the methods and learn simultaneously from both kinds of information.
Book Reviews, Robert Moll
Book Reviews, Robert Moll
Computer Science Department Faculty Publication Series
No abstract provided.
Associative Search Network: A Reinforcement Learning Associative Memory, Andrew G. Barto, Richard S. Sutton, Peter S. Brouwer
Associative Search Network: A Reinforcement Learning Associative Memory, Andrew G. Barto, Richard S. Sutton, Peter S. Brouwer
Computer Science Department Faculty Publication Series
An associative memory system is presented which does not require a "teacher" to provide the desired associations. For each input key it conducts a search for the output pattern which optimizes an external payoff or reinforcement signal. The associative search network (ASN) combines pattern recognition and function optimization capabilities in a simple and effective way. We define the associative search problem, discuss conditions under which the associative search network is capable of solving it, and present results from computer simulations. The synthesis of sensory-motor control surfaces is discussed as an example of the associative search problem.