Results 1 - 10 of 8,423

A Learning Algorithm for Continually Running Fully Recurrent Neural Networks

by Ronald J. Williams, David Zipser , 1989
"... The exact form of a gradient-following learning algorithm for completely recurrent networks running in continually sampled time is derived and used as the basis for practical algorithms for temporal supervised learning tasks. These algorithms have: (1) the advantage that they do not require a precis ..."
Abstract - Cited by 534 (4 self) - Add to MetaCart
precisely defined training interval, operating while the network runs; and (2) the disadvantage that they require nonlocal communication in the network being trained and are computationally expensive. These algorithms are shown to allow networks having recurrent connections to learn complex tasks requiring

A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection

by Ron Kohavi - INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE , 1995
"... We review accuracy estimation methods and compare the two most common methods: cross-validation and bootstrap. Recent experimental results on artificial data and theoretical results in restricted settings have shown that for selecting a good classifier from a set of classifiers (model selection), te ..."
Abstract - Cited by 1283 (11 self) - Add to MetaCart
), ten-fold cross-validation may be better than the more expensive leaveone-out cross-validation. We report on a largescale experiment -- over half a million runs of C4.5 and a Naive-Bayes algorithm -- to estimate the effects of different parameters on these algorithms on real-world datasets. For cross

Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms

by Thomas G. Dietterich , 1998
"... This article reviews five approximate statistical tests for determining whether one learning algorithm outperforms another on a particular learning task. These tests are compared experimentally to determine their probability of incorrectly detecting a difference when no difference exists (type I err ..."
Abstract - Cited by 723 (8 self) - Add to MetaCart
by the computational cost of running the learning algorithm. For algorithms that can be executed only once, Mc-Nemar’s test is the only test with acceptable type I error. For algorithms that can be executed 10 times, the 5×2 cv test is recommended, because it is slightly more powerful and because it directly measures

The Implementation of the Cilk-5 Multithreaded Language

by Matteo Frigo, Charles E. Leiserson, Keith H. Randall , 1998
"... The fifth release of the multithreaded language Cilk uses a provably good "work-stealing " scheduling algorithm similar to the rst system, but the language has been completely redesigned and the runtime system completely reengineered. The efficiency of the new implementation was aided ..."
Abstract - Cited by 489 (28 self) - Add to MetaCart
by a clear strategy that arose from a theoretical analysis of the scheduling algorithm: concentrate on minimizing overheads that contribute to the work, even at the expense of overheads that contribute to the critical path. Although it may seem counterintuitive to move overheads onto the critical path

The Paradyn Parallel Performance Measurement Tools

by Barton P. Miller, Mark D. Callaghan, Jonathan M. Cargille, Jeffrey K. Hollingsworth, R. Bruce Irvin , Karen L. Karavanic, Krishna Kunchithapadam, Tia Newhall - IEEE COMPUTER , 1995
"... Paradyn is a performance measurement tool for parallel and distributed programs. Paradyn uses several novel technologies so that it scales to long running programs (hours or days) and large (thousand node) systems, and automates much of the search for performance bottlenecks. It can provide precise ..."
Abstract - Cited by 447 (39 self) - Add to MetaCart
Paradyn is a performance measurement tool for parallel and distributed programs. Paradyn uses several novel technologies so that it scales to long running programs (hours or days) and large (thousand node) systems, and automates much of the search for performance bottlenecks. It can provide precise

Bullet: High Bandwidth Data Dissemination Using an Overlay Mesh

by Dejan Kostic, Adolfo Rodriguez, Jeannie Albrecht, Amin Vahdat , 2003
"... In recent years, overlay networks have become an effective alternative to IP multicast for efficient point to multipoint communication across the Internet. Typically, nodes self-organize with the goal of forming an efficient overlay tree, one that meets performance targets without placing undue burd ..."
Abstract - Cited by 424 (22 self) - Add to MetaCart
such that any data object is equally likely to appear at any node, ii) a scalable and decentralized algorithm that allows nodes to locate and recover missing data items, and iii) a complete implementation and evaluation of Bullet running across the Internet and in a large-scale emulation environment reveals up

gprof: a Call Graph Execution Profiler

by Susan L. Graham, Peter B. Kessler, Marshall K. McKusick , 1982
"... Large complex programs are composed of many small routines that implement abstractions for the routines that call them. To be useful, an execution profiler must attribute execution time in a way that is significant for the logical structure of a program as well as for its textual decomposition. This ..."
Abstract - Cited by 414 (0 self) - Add to MetaCart
. This data must then be displayed to the user in a convenient and informative way. The gprof profiler accounts for the running time of called routines in the running time of the routines that call them. The design and use of this profiler is described. 1. Programs to be Profiled Software research

Combating web spam with trustrank

by Zoltán Gyöngyi, Hector Garcia-molina, Jan Pedersen - In VLDB , 2004
"... Web spam pages use various techniques to achieve higher-than-deserved rankings in a search engine’s results. While human experts can identify spam, it is too expensive to manually evaluate a large number of pages. Instead, we propose techniques to semi-automatically separate reputable, good pages fr ..."
Abstract - Cited by 413 (3 self) - Add to MetaCart
Web spam pages use various techniques to achieve higher-than-deserved rankings in a search engine’s results. While human experts can identify spam, it is too expensive to manually evaluate a large number of pages. Instead, we propose techniques to semi-automatically separate reputable, good pages

Simulating the power consumption of large-scale sensor network applications

by Victor Shnayder, Mark Hempstead, Bor-rong Chen, Geoff Werner Allen, Matt Welsh - In Sensys , 2004
"... Developing sensor network applications demands a new set of tools to aid programmers. A number of simulation environments have been developed that provide varying degrees of scalability, realism, and detail for understanding the behavior of sensor networks. To date, however, none of these tools have ..."
Abstract - Cited by 327 (4 self) - Add to MetaCart
for TinyOS applications. In PowerTOSSIM, TinyOS components corresponding to specific hardware peripherals (such as the radio, EEPROM, LEDs, and so forth) are instrumented to obtain a trace of each device’s activity during the simulation run. PowerTOSSIM employs a novel code-transformation technique

On-line Fingerprint Verification

by Anil Jain, Lin Hong, Ruud Bolle - IEEE Transactions on Pattern Analysis and Machine Intelligence , 1997
"... Abstract—Fingerprint verification is one of the most reliable personal identification methods. However, manual fingerprint verification is so tedious, time-consuming, and expensive that it is incapable of meeting today’s increasing performance requirements. An automatic fingerprint identification sy ..."
Abstract - Cited by 300 (32 self) - Add to MetaCart
Abstract—Fingerprint verification is one of the most reliable personal identification methods. However, manual fingerprint verification is so tedious, time-consuming, and expensive that it is incapable of meeting today’s increasing performance requirements. An automatic fingerprint identification
Results 1 - 10 of 8,423