检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM) - Human Genomics

作者： Rogers, John D. De Paul Univ Sch Comp Chicago IL 60604 USA

ISBN: (纸本)9781538654880

The Normalized compression Distance (NCD) method, which provides difference matrices from which phylogenetic trees can be constructed, is computationally very fast even on large sets of sequences. The Markov Chain Monte Carlo (MCMC) method, widely used in the literature, is computationally more expensive but is relied on as an accurate method for constructing trees. We look here at results comparing these methods with respect to unrooted quartet trees, which can serve as building blocks for deriving trees on larger sets of sequences.

关键词： compression algorithms Phylogeny Markov processes Monte Carlo methods DNA Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Evolving Structures in Complex Systems

Evolving Structures in Complex Systems

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Hugo Cisneros Josef Sivic Tomas Mikolov CIIRC CTU in Prague ENS Paris-Saclay Inria DI-ENS PSL CIIRC CTU in Prague Facebook AI

The following topics are dealt with: learning (artificial intelligence); feature extraction; neural nets; evolutionary computation; optimisation; genetic algorithms; search problems; convolutional neural nets; image c... 详细信息

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

关键词： Automata Complexity theory Measurement Complex systems Organisms compression algorithms Tungsten

来源：评论

学校读者我要写书评

暂无评论

LARGE-SCALE HYPERSPECTRAL IMAGE compression VIA SPARSE REPRESENTATIONS BASED ON ONLINE LEARNING

引用

INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE 2018年第1期28卷 197-207页

作者： Ulku, Irem Kizgut, Ersin Cankaya Univ Dept Elect & Elect Engn Eskisehir Yolu 29 km TR-06790 Ankara Turkey Univ Politecn Valencia Univ Inst Pure & Appl Math IUMPA E-46071 Valencia Spain

In this study, proximity based optimization algorithms are used for lossy compression of hyperspectral images that are inherently large scale. This is the first time that such proximity based optimization algorithms are implemented with an online dictionary learning method. compression performances are compared with the one obtained by various sparse representation algorithms. As a result, proximity based optimization algorithms are listed among the three best ones in terms of compression performance values for all hyperspectral images. Additionally, the applicability of anomaly detection is tested on the reconstructed images.

关键词： hyperspectral imaging compression algorithms dictionary learning sparse coding

来源：评论

学校读者我要写书评

暂无评论

Activations Quantization for Compact Neural Networks 23

Activations Quantization for Compact Neural Networks

引用

23rd IEEE International Conference on Digital Signal Processing (DSP)

作者： Wei, Yadong Zhao, Zhixu Taoyang Zhen, Zishuo Hao, Zeyu Ren, Pengju Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Shaanxi Peoples R China

ISBN: (纸本)9781538668122;9781538668115

As optimizing neural networks to improve processing speed has become a necessary process in industrial deployment, emerging challenges due to limited storage and computation when adopting neural networks on embedded system need to be addressed. There are some previous studies focusing on training neural networks with low precision weights and activations, like Binarized neural network and DoReFa-Net. Meanwhile, an alternative approach is deployed to reduce number of operations and model size, like MobileNet and SqueezeNet. In this work, by adopting SQ(Scale Quantization) method to quantify activations of each neuron, we have gained a more satisfying result especially in compact network models. For SqueezeDet on KITTI dataset, SQ achieves 22.86% more accuracy on means correct detections, while means location and classification error decrease by 41.84% and 68.57%, compared with DoReFa-Net with 2-bits activations. Additionally, we also propose the SQT(Scale Quantization with Threshold) method to further improve the quantization flexibility. It is worth mentioned that our approach is primarily designed for activations quantization, but it can also be complemented with other orthogonal methods to further achieving efficient neural network processing at the edge.

关键词： Biological neural networks Quantization (signal) compression algorithms Neurons Training Computational modeling

来源：评论

学校读者我要写书评

暂无评论

RePair in Compressed Space and Time

RePair in Compressed Space and Time

引用

Data compression Conference (DCC)

作者： Kensuke Sakai Tatsuya Ohno Keisuke Goto Yoshimasa Takabatake I. Tomohiro Hiroshi Sakamoto Kyushu Institute of Technology Japan Fujitsu Laboratories Ltd. Japan Kyushu Kogyo Daigaku Kitakyushu Fukuoka JP

Given a string T of length N, the goal of grammar compression is to construct a small context-free grammar generating only T. Among existing grammar compression methods, RePair (recursive paring) [Larsson and Moffat, 1999] is notable for achieving good compression ratios in practice. In this paper, we propose the first RePair algorithm working in compressed space, i.e., potentially o(N) space for highly compressible texts. The key idea is to give a new way to restructure an arbitrary (context-free) grammar S for T into RePair(T) in compressed space and time. We propose an algorithm for RePair(T) running in O(min(N, nm log N)) space and expected O(min(N, nm log N) m) time or O(min(N, nm log N) log log N) time, where n is the size of S and m is the number of variables in RePair(T). We implemented our O(min(N, nm log N) m)-time algorithm and show it can actually run in compressed space. We also present a new approach to reduce the peak memory usage of existing RePair algorithms combining with our algorithms, and show that the new approach outperforms, both in computation time and space, the most space efficient linear-time RePair implementation to date.

关键词： Maintenance engineering Grammar compression algorithms Production Time complexity Frequency measurement

来源：评论

学校读者我要写书评

暂无评论

A Network-Centric Hardware/Algorithm Co-Design to Accelerate Distributed Training of Deep Neural Networks 51

A Network-Centric Hardware/Algorithm Co-Design to Accelerate...

引用

51st Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)

作者： Li, Youjie Park, Jongse Alian, Mohammad Yuan, Yifan Qu, Zheng Pan, Peitian Wang, Ren Schwing, Alexander Gerhard Esmaeilzadeh, Hadi Kim, Nam Sung Univ Illinois Urbana IL 61801 USA Georgia Inst Technol Atlanta GA 30332 USA Tsinghua Univ Beijing Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples R China Intel Corp Santa Clara CA 95051 USA Univ Calif San Diego San Diego CA 92103 USA

ISBN: (纸本)9781538662403

Training real-world Deep Neural Networks (DNNs) can take an eon (i.e., weeks or months) without leveraging distributed systems. Even distributed training takes inordinate time, of which a large fraction is spent in communicating weights and gradients over the network. State-of-the-art distributed training algorithms use a hierarchy of worker-aggregator nodes. The aggregators repeatedly receive gradient updates from their allocated group of the workers, and send back the updated weights. This paper sets out to reduce this significant communication cost by embedding data compression accelerators in the Network Interface Cards (NICs). To maximize the benefits of in-network acceleration, the proposed solution, named INCEPTIONN (In-Network Computing to Exchange and Process Training Information Of Neural Networks), uniquely combines hardware and algorithmic innovations by exploiting the following three observations. (1) Gradients are significantly more tolerant to precision loss than weights and as such lend themselves better to aggressive compression without the need for the complex mechanisms to avert any loss. (2) The existing training algorithms only communicate gradients in one leg of the communication, which reduces the opportunities for in-network acceleration of compression. (3) The aggregators can become a bottleneck with compression as they need to compress/decompress multiple streams from their allocated worker group. To this end, we first propose a lightweight and hardware friendly lossy-compression algorithm for floating-point gradients, which exploits their unique value characteristics. This compression not only enables significantly reducing the gradient communication with practically no loss of accuracy, but also comes with low complexity for direct implementation as a hardware block in the NIC. To maximize the opportunities for compression and avoid the bottleneck at aggregators, we also propose an aggregator-free training algorithm that exchanges gradien

关键词： Training Neural networks Hardware Acceleration Complexity theory compression algorithms Distributed databases

来源：评论

学校读者我要写书评

暂无评论

Acquisition and Reducing of Redundancy of Measuring Information on the basis of National Instruments Reconfigurable Input-output Modules in Technical System Diagnosis

Acquisition and Reducing of Redundancy of Measuring Informat...

引用

International Russian Automation Conference (RusAutoCon)

作者： Levoniuk Sergey Ginis Larisa Gordienko Larisa Dept. of Information measuring technologies and systems Southern Federal University Taganrog Russia

The article discusses the possibility of using National Instruments reconfigurable input-output modules in technical diagnostics systems. A significant amount of input measurement information in the diagnosis and, at the same time, its redundancy leads to the need for reversible data compression using first and zero order aperture extrapolation and interpolation algorithms. In this case, the input measurement signals can be further restored as a function of time with a given error. The compression algorithms simulations were performed to verify their correctness and efficiency. Data compression virtual instruments implemented on the basis of reconfigurable modules were developed and tested using the National Instruments LabVIEW graphical programming environment. The advantage of the offer is that the reconfigurable module device development is reduced only to the module programmable logic integrated circuit configuration. After programming, the modules can function as part of a personal or industrial computer.

关键词： Instruments Field programmable gate arrays Data compression Extrapolation Automation Time measurement compression algorithms

来源：评论

学校读者我要写书评

暂无评论

Hybrid AES-Huffman Coding for Secure Lossless Transmission

Hybrid AES-Huffman Coding for Secure Lossless Transmission

引用

International Conference on Informatics and Computing (ICIC)

作者： Mutia Rizky Ashila Nur Atikah De Rosal Ignatius Moses Setiadi Eko Hari Rachmawanto Christy Atika Sari Dian Nuswantoro University Semarang Indonesia

Encoding is one of the effective ways to secure files, both for storing and sending files through the public network. Advanced Encryption Standard (AES) is one of the most powerful encryption algorithms that are widely used in various researches and implemented in hardware and software. But this algorithm has negative side effects, which can increase file size. The lossless Huffman compression algorithm can be used to overcome these side effects. But after reviewing the relevant research, the effect of compression on encrypted files is not discussed in detail. This research proposes a combination of AES-Huffman to produce lossless compressed encryption files. Where encryption is done first, then the compression process is carried out. To find out the quality of file security, measurements were made using the avalanche effect (AE) and entropy after encryption and compression. Based on the test results it is proven true that AES encryption has side effects in increasing file size around 25% of the original file size. But after Huffman compression the encrypted file code shrank by around 30%, meaning that the file size after being compressed was smaller than the original file size. However, from the aspect of security, the Huffman file gives a positive effect, where there is a significant increase in the value of AE and entropy.

关键词： Encryption Entropy Informatics compression algorithms Encoding

来源：评论

学校读者我要写书评

暂无评论

Compressed Cache Layout Aware Prefetching

Compressed Cache Layout Aware Prefetching

引用

International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)

作者： Niloofar Charmchi Caroline Collange André Seznec Inria IRISA

The speed gap between CPU and memory is impairing performance. Cache compression and hardware prefetching are two techniques that could confront this bottleneck by decreasing last level cache misses. However, compression and prefetching have positive interactions, as prefetching benefits from higher cache capacity and compression increases the effective cache size. This paper proposes Compressed cache Layout Aware Prefetching (CLAP) to leverage the recently proposed sector-based compressed cache layouts such as SCC or YACC to create a synergy between compressed cache and prefetching. The idea of this approach is to prefetch contiguous blocks that can be compressed and co-allocated together with the requested block on a miss access. Prefetched blocks that share storage with existing blocks do not need to evict a valid existing entry; therefore, CLAP avoids cache pollution. In order to decide the co-allocatable blocks to prefetch, we propose a compression predictor. Based on our experimental evaluations, CLAP reduces the number of cache misses by 12% and improves performance by 4% on average, comparing to a compressed cache.

关键词： Prefetching Layout Hardware Compaction Pollution Benchmark testing compression algorithms

来源：评论

学校读者我要写书评

暂无评论

CP based OFDM Radar Range Reconstruction under the Background of Fragmented Spectrum (Poster)

CP based OFDM Radar Range Reconstruction under the Backgroun...

引用

International Conference on Information Fusion

作者： Xinyu Liu Tianxian Zhang Qiao Shi Lingjiang Kong School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu Sichuan China

ISBN: (数字)9780996452786

ISBN: (纸本)9781728118406

In this paper, considering the limitation of spectrum resource scarcity to the classical CP-OFDM method in the radar applications, a range reconstruction model based on CP-OFDM is investigated on the background of fragmented spectrum. To match the bandwidth of available fragmented spectrums, original OFDM subcarriers are arbitrarily divided into several resource blocks (RB) and modulated into the desired frequency sub-bands firstly. Then, a sufficient cyclic prefix (CP) is added to each resource block OFDM pulse to guarantee the inter-range-cell interference (IRCI) free in our constructed transceiver signal model. Besides, a range compression algorithm is presented, acquiring nearly zero sidelobes in the range profile. Analysis about the point spread function with zero doppler of RB-CP-OFDM and simulation results about the range reconstruction show that the proposed method can provide satisfactory performances.

关键词： OFDM Bandwidth Frequency modulation Interference Transceivers compression algorithms Simulation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：