Results 1 - 10 of 2,729

A fast learning algorithm for deep belief nets

by Geoffrey E. Hinton, Simon Osindero - Neural Computation , 2006
"... We show how to use “complementary priors ” to eliminate the explaining away effects that make inference difficult in densely-connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer at a ..."
Abstract - Cited by 970 (49 self) - Add to MetaCart
We show how to use “complementary priors ” to eliminate the explaining away effects that make inference difficult in densely-connected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer

Training Support Vector Machines: an Application to Face Detection

by Edgar Osuna, Robert Freund, Federico Girosi , 1997
"... We investigate the application of Support Vector Machines (SVMs) in computer vision. SVM is a learning technique developed by V. Vapnik and his team (AT&T Bell Labs.) that can be seen as a new method for training polynomial, neural network, or Radial Basis Functions classifiers. The decision sur ..."
Abstract - Cited by 727 (1 self) - Add to MetaCart
surfaces are found by solving a linearly constrained quadratic programming problem. This optimization problem is challenging because the quadratic form is completely dense and the memory requirements grow with the square of the number of data points. We present a decomposition algorithm that guarantees

The Stanford FLASH multiprocessor

by Jeffrey Kuskin, David Ofelt, Mark Heinrich, John Heinlein, Richard Simoni, Kourosh Gharachorloo, John Chapin, David Nakahira, Joel Baxter, Mark Horowitz, Anoop Gupta, Mendel Rosenblum, John Hennessy - In Proceedings of the 21st International Symposium on Computer Architecture , 1994
"... The FLASH multiprocessor efficiently integrates support for cache-coherent shared memory and high-performance message passing, while minimizing both hardware and software overhead. Each node in FLASH contains a microprocessor, a portion of the machine’s global memory, a port to the interconnection n ..."
Abstract - Cited by 349 (20 self) - Add to MetaCart
The FLASH multiprocessor efficiently integrates support for cache-coherent shared memory and high-performance message passing, while minimizing both hardware and software overhead. Each node in FLASH contains a microprocessor, a portion of the machine’s global memory, a port to the interconnection

Algorithms and data structures for flash memories

by Eran Gal, Sivan Toledo - ACM Computing Surveys
"... Flash memory is a type of electrically-erasable programmable read-only memory (EEPROM). Because flash memories are nonvolatile and relatively dense, they are now used to store files and other persistent objects in handheld computers, mobile phones, digital cameras, portable music players, and many o ..."
Abstract - Cited by 192 (4 self) - Add to MetaCart
Flash memory is a type of electrically-erasable programmable read-only memory (EEPROM). Because flash memories are nonvolatile and relatively dense, they are now used to store files and other persistent objects in handheld computers, mobile phones, digital cameras, portable music players, and many

Bug Isolation via Remote Program Sampling

by Ben Liblit, Alex Aiken, Alice X. Zheng, Michael I. Jordan - In Proceedings of the ACM SIGPLAN 2003 Conference on Programming Language Design and Implementation , 2003
"... We propose a low-overhead sampling infrastructure for gathering information from the executions experienced by a program 's user community. Several example applications illustrate ways to use sampled instrumentation to isolate bugs. Assertion-dense code can be transformed to share the cost of a ..."
Abstract - Cited by 335 (16 self) - Add to MetaCart
We propose a low-overhead sampling infrastructure for gathering information from the executions experienced by a program 's user community. Several example applications illustrate ways to use sampled instrumentation to isolate bugs. Assertion-dense code can be transformed to share the cost

Cartel: a distributed mobile sensor computing system

by Bret Hull, Vladimir Bychkovsky, Yang Zhang, Kevin Chen, Michel Goraczko, Allen Miu, Eugene Shih, Hari Balakrishnan, Samuel Madden - In 4th ACM SenSys , 2006
"... CarTel is a mobile sensor computing system designed to collect, process, deliver, and visualize data from sensors located on mobile units such as automobiles. A CarTel node is a mobile embedded computer coupled to a set of sensors. Each node gathers and processes sensor readings locally before deliv ..."
Abstract - Cited by 327 (30 self) - Add to MetaCart
of heterogeneous data from sensors, and handles intermittent and variable network connectivity. CarTel nodes rely primarily on opportunistic wireless (e.g., Wi-Fi, Bluetooth) connectivity—to the Internet, or to “data mules ” such as other CarTel nodes, mobile phone flash memories, or USB keys—to communicate

Benchmarking GPUs to tune dense linear algebra

by Vasily Volkov, James W. Demmel, Geforce Geforce, Geforce Geforce , 2008
"... We present performance results for dense linear algebra using recent NVIDIA GPUs. Our matrix-matrix multiply routine (GEMM) runs up to 60 % faster than the vendor’s implementation and approaches the peak of hardware capabilities. Our LU, QR and Cholesky factorizations achieve up to 80–90 % of the pe ..."
Abstract - Cited by 242 (2 self) - Add to MetaCart
We present performance results for dense linear algebra using recent NVIDIA GPUs. Our matrix-matrix multiply routine (GEMM) runs up to 60 % faster than the vendor’s implementation and approaches the peak of hardware capabilities. Our LU, QR and Cholesky factorizations achieve up to 80

A flash-memory based file system

by Atsuo Kawaguchi, Shingo Nishioka, Hiroshi Motoda - IN USENIX TECHNICAL CONFERENCE ON UNIX AND ADVANCED COMPUTING SYSTEMS , 1995
"... A flash memory device driver that supports a conventional UNIX file system transparently was designed. To avoid the limitations due to flash memory's restricted number of write cycles and its inability to be overwritten, this driver writes data to the flash memory system sequentially as a Log-s ..."
Abstract - Cited by 149 (0 self) - Add to MetaCart
A flash memory device driver that supports a conventional UNIX file system transparently was designed. To avoid the limitations due to flash memory's restricted number of write cycles and its inability to be overwritten, this driver writes data to the flash memory system sequentially as a Log

A supernodal approach to sparse partial pivoting

by James W. Demmel, Stanley C. Eisenstat, John R. Gilbert, Xiaoye S. Li, Joseph W. H. Liu - SIAM Journal on Matrix Analysis and Applications , 1999
"... We investigate several ways to improve the performance of sparse LU factorization with partial pivoting, as used to solve unsymmetric linear systems. To perform most of the numerical computation in dense matrix kernels, we introduce the notion of unsymmetric supernodes. To better exploit the memory ..."
Abstract - Cited by 262 (25 self) - Add to MetaCart
We investigate several ways to improve the performance of sparse LU factorization with partial pivoting, as used to solve unsymmetric linear systems. To perform most of the numerical computation in dense matrix kernels, we introduce the notion of unsymmetric supernodes. To better exploit the memory

Rank modulation for flash memories

by Anxiao (Andrew) Jiang, Robert Mateescu, Moshe Schwartz, Jehoshua Bruck , 2009
"... We explore a novel data representation scheme for multilevel flash memory cells, in which a set of n cells stores information in the permutation induced by the different charge levels of the individual cells. The only allowed charge-placement mechanism is a “push-to-the-top” operation, which takes a ..."
Abstract - Cited by 100 (41 self) - Add to MetaCart
We explore a novel data representation scheme for multilevel flash memory cells, in which a set of n cells stores information in the permutation induced by the different charge levels of the individual cells. The only allowed charge-placement mechanism is a “push-to-the-top” operation, which takes
Results 1 - 10 of 2,729