scispace - formally typeset
Search or ask a question
Topic

Redundancy (engineering)

About: Redundancy (engineering) is a research topic. Over the lifetime, 28243 publications have been published within this topic receiving 400653 citations. The topic is also known as: redundant system & engineered redundancy.


Papers
More filters
Proceedings Article
Emily Denton1, Wojciech Zaremba1, Joan Bruna1, Yann LeCun1, Rob Fergus1 
08 Dec 2014
TL;DR: In this paper, the authors exploit the redundancy present within the convolutional filters to derive approximations that significantly reduce the required computation, while keeping the accuracy within 1% of the original model.
Abstract: We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. These models deliver impressive accuracy, but each image evaluation requires millions of floating point operations, making their deployment on smartphones and Internet-scale clusters problematic. The computation is dominated by the convolution operations in the lower layers of the model. We exploit the redundancy present within the convolutional filters to derive approximations that significantly reduce the required computation. Using large state-of-the-art models, we demonstrate speedups of convolutional layers on both CPU and GPU by a factor of 2 x, while keeping the accuracy within 1% of the original model.

1,342 citations

Journal ArticleDOI
TL;DR: This article provides an overview of H.263, the new ITU-T Recommendation for low-bit-rate video communication, which specifies a coded representation for compressing the moving picture component of audio-visual signals at low bit rates.
Abstract: This article provides an overview of H.263, the new ITU-T Recommendation for low-bit-rate video communication. H.263 specifies a coded representation for compressing the moving picture component of audio-visual signals at low bit rates. The basic structure of the video source coding algorithm is taken from ITU-T Recommendation H.261 and is a hybrid of interpicture prediction to reduce temporal redundancy and transform coding of the prediction residual to reduce spatial redundancy. The source coder can operate on five standardized picture formats: sub-QCIF, QCIF, CIF, 4CIF, and 16CIF. The decoder has motion compensation capability with half-pixel precision, in contrast to H.261 which uses full-pixel precision and employs a loop filter. H.263 includes four negotiable coding options which provide improved coding efficiency: unrestricted motion vectors, syntax-based arithmetic coding, advanced prediction, and PB-frames.

1,294 citations

Patent
14 May 2002
TL;DR: In this article, the data is divided into segments and each segment is distributed randomly on one of several storage units, independent of the storage units on which other segments of the media data are stored.
Abstract: Multiple applications request data from multiple storage units over a computer network. The data is divided into segments and each segment is distributed randomly on one of several storage units, independent of the storage units on which other segments of the media data are stored. Redundancy information corresponding to each segment also is distributed randomly over the storage units. The redundancy information for a segment may be a copy of the segment, such that each segment is stored on at least two storage units. The redundancy information also may be based on two or more segments. This random distribution of segments of data and corresponding redundancy information improves both scalability and reliability. When a storage unit fails, its load is distributed evenly over to remaining storage units and its lost data may be recovered because of the redundancy information. When an application requests a selected segment of data, the request may be processed by the storage unit with the shortest queue of requests. Random fluctuations in the load applied by multiple applications on multiple storage units are balanced nearly equally over all of the storage units. Small data files also may be stored on storage units that combine small files into larger segments of data using a log structured file system. This combination of techniques results in a system which can transfer both multiple, independent high-bandwidth streams of data and small data files in a scalable manner in both directions between multiple applications and multiple storage units.

1,195 citations

Proceedings ArticleDOI
28 Sep 2002
TL;DR: A node-scheduling scheme, which can reduce system overall energy consumption, therefore increasing system lifetime, by turning off some redundant nodes, and guarantees that the original sensing coverage is maintained after turning off redundant nodes.
Abstract: In wireless sensor networks that consist of a large number of low-power, short-lived, unreliable sensors, one of the main design challenges is to obtain long system lifetime, as well as maintain sufficient sensing coverage and reliability. In this paper, we propose a node-scheduling scheme, which can reduce system overall energy consumption, therefore increasing system lifetime, by turning off some redundant nodes. Our coverage-based off-duty eligibility rule and backoff-based node-scheduling scheme guarantees that the original sensing coverage is maintained after turning off redundant nodes. We implement our proposed scheme in NS-2 as an extension of the LEACH protocol. We compare the energy consumption of LEACH with and without the extension and analyze the effectiveness of our scheme in terms of energy saving. Simulation results show that our scheme can preserve the system coverage to the maximum extent. In addition, after the node-scheduling scheme turns off some nodes, certain redundancy is still guaranteed, which we believe can provide enough sensing reliability in many applications.

1,179 citations

Proceedings ArticleDOI
15 May 2014
TL;DR: Two simple schemes for drastically speeding up convolutional neural networks are presented, achieved by exploiting cross-channel or filter redundancy to construct a low rank basis of filters that are rank-1 in the spatial domain.
Abstract: The focus of this paper is speeding up the application of convolutional neural networks. While delivering impressive results across a range of computer vision and machine learning tasks, these networks are computationally demanding, limiting their deployability. Convolutional layers generally consume the bulk of the processing time, and so in this work we present two simple schemes for drastically speeding up these layers. This is achieved by exploiting cross-channel or filter redundancy to construct a low rank basis of filters that are rank-1 in the spatial domain. Our methods are architecture agnostic, and can be easily applied to existing CPU and GPU convolutional frameworks for tuneable speedup performance. We demonstrate this with a real world network designed for scene text character recognition [15], showing a possible 2.5× speedup with no loss in accuracy, and 4.5× speedup with less than 1% drop in accuracy, still achieving state-of-the-art on standard benchmarks.

1,159 citations


Network Information
Related Topics (5)
Artificial neural network
207K papers, 4.5M citations
87% related
Wireless sensor network
142K papers, 2.4M citations
86% related
Cluster analysis
146.5K papers, 2.9M citations
86% related
Network packet
159.7K papers, 2.2M citations
86% related
Feature extraction
111.8K papers, 2.1M citations
86% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
20231,321
20222,888
20211,167
20201,305
20191,449
20181,375