检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Feng, Weijiang Guan, Naiyang Li, Yuan Zhang, Xiang Luo, Zhigang Natl Univ Def Technol Coll Comp Inst Software Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Sci & Technol Parallel & Distributed Lab Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781509061822

Studies on nowadays human-machine interface have demonstrated that visual information can enhance speech recognition accuracy especially in noisy environments. Deep learning has been widely used to tackle such audio visual speech recognition (AVSR) problem due to its astonishing achievements in both speech recognition and image recognition. Although existing deep learning models succeed to incorporate visual information into speech recognition, none of them simultaneously considers sequential characteristics of both audio and visual modalities. To overcome this deficiency, we proposed a multimodal recurrent neural network (multimodal RNN) model to take into account the sequential characteristics of both audio and visual modalities for AVSR. In particular, multimodal RNN includes three components, i.e., audio part, visual part, and fusion part, where the audio part and visual part capture the sequential characteristics of audio and visual modalities, respectively, and the fusion part combines the outputs of both modalities. Here we modelled the audio modality by using a LSTM RNN, and modelled the visual modality by using a convolutional neural network (CNN) plus a LSTM RNN, and combined both models by a multimodal layer in the fusion part. We validated the effectiveness of the proposed multimodal RNN model on a multi-speaker AVSR benchmark dataset termed AVletters. The experimental results show the performance improvements comparing to the known highest audio visual recognition accuracies on AVletters, and confirm the robustness of our multimodal RNN model.

关键词： Audio visual speech recognition deep learning multimodal learning recurrent neural networks LSTM

来源：评论

学校读者我要写书评

暂无评论

Prophet: A parallel Instruction-Oriented Many-Core Simulator

引用

IEEE TRANSACTIONS ON parallel AND distributed SYSTEMS 2017年第10期28卷 2939-2952页

作者： Zhang, Weihua Ji, Xiaofeng Lu, Yunping Wang, Haojun Chen, Haibo Yew, Pen-Chung Fudan Univ Software Sch Shanghai Key Lab Data Sci Shanghai 200433 Peoples R China Fudan Univ Parallel Proc Inst Shanghai 200433 Peoples R China Fudan Univ Sch Comp Sci Shanghai Key Lab Data Sci Shanghai 200433 Peoples R China Shanghai Jiao Tong Univ Inst Parallel & Distributed Syst Shanghai 200240 Peoples R China Univ Minnesota Dept Comp Sci & Engn Minneapolis MN 55455 USA

Most existing computer architecture simulators are cycle oriented, i.e., they are driven cycle by cycle. However, frequent switches among simulation contexts, excessive buffer accesses and tightly coupled manner often make such an architecture simulator slow, difficult to parallelize and hard to scale to large-scale many-core systems. In this paper, we propose Prophet, a parallel instruction-oriented simulation framework for many-cores. Prophet adopts a general instruction-oriented model to simulate processor cores, in which a simulator is built from the perspective of each simulated instruction impacting a small number of relevant processor components, as opposed to that of a large number of processor components executing many instructions in each cycle as in the cycle-oriented approach. Prophet determines the execution cycle of a simulated instruction based on the states of the relevant components impacted by the instruction, and update the components states after the execution of the instruction. Prophet also adopts a speculative model to decouple private resources from the shared resources (e.g., shared cache), which avoids unnecessary interactions between them and only pays a penalty upon a rare mis-speculation. We have designed and implemented a prototype of Prophet that supports both user-level and full-system simulation. Experimental results show Prophet can scale up to simulate thousands of simulated cores (4,096 cores in the current implementation) with good performance and small accuracy loss. It achieves average simulation speeds of about 98 and 235 MIPS (millions of simulated instructions per second) for full-system and user-level simulation, respectively, with only 3 percent IPC error rate and negligible deviation in cache simulation results. When run on a many-core platform (i.e., Intel Xeon Phi), it achieved an average simulation speed of about 413 MIPS.

关键词： Instruction-oriented parallel manycore simulation architecture-simulation

来源：评论

学校读者我要写书评

暂无评论

A Loosely-Coupled Full-System Multicore Simulation Framework

引用

IEEE TRANSACTIONS ON parallel AND distributed SYSTEMS 2016年第6期27卷 1566-1578页

作者： Zhang, Weihua Wang, Haojun Lu, Yunping Chen, Haibo Zhao, Wenyun Fudan Univ Software Sch Shanghai 200433 Peoples R China Fudan Univ Shanghai Key Lab Data Sci Shanghai 200433 Peoples R China Fudan Univ Parallel Proc Inst Shanghai 200433 Peoples R China Fudan Univ Sch Comp Sci Shanghai 200433 Peoples R China Shanghai Jiao Tong Univ Inst Parallel & Distributed Syst Shanghai 200030 Peoples R China

Full-system simulation is critical in evaluating design alternatives for multicore processors. However, state-of-the-art multicore simulators either lack good extensibility due to their tightly-coupled design between functional model (FM) and timing model (TM), or cannot guarantee cycle-accuracy. This paper conducts a comprehensive study on factors affecting cycle-accuracy and uncovers several contributing factors less studied before. Based on these insights, we propose a loosely-coupled functional-driven full-system simulator for multicore, namely Transformer. To ensure extensibility and cycle-accuracy, Transformer leverages an architecture-independent interface between FM and TM and uses a lightweight scheme to detect and recover from execution divergence between FM and TM. Built upon Transformer and its foundational simulator components, a graduate student only needed to write about 180 lines of code to extend an X86 functional model (QEMU) in Transformer. Moreover, the loosely-coupled design also removes the complex interaction between FM and TM and opens the opportunity to parallelize FM and TM to improve performance. Experimental results show that Transformer achieves an average of 8.4 and 7.0 percent performance improvement over GEMS in 4-core and 8-core configuration while guaranteeing cycle-accuracy. A further parallelization between FM and TM leads to 35.3 and 29.7 percent performance improvement respectively.

关键词： Functional-driven multicore simulation full-system extension

来源：评论

学校读者我要写书评

暂无评论

A Rigorous Model of Service Component Architecture

引用

ELECTRONIC NOTES IN THEORETICAL COMPUTER SCIENCE 2008年第C期207卷 33-48页

作者： Ding, Zuohua Chen, Zhenbang Liu, Jing Zhejiang Sci Tech Univ Ctr Math Comp & Software Engn Hangzhou 310018 Peoples R China United Nations Univ Int Inst Software Technol Tokyo Japan Natl Lab Parallel & Distributed Proc Changsha 410073 Hunan Peoples R China East China Normal Univ Inst Theoret Comp Shanghai 200062 Peoples R China

The Service Component Architecture (SCA) provides a platform-independent component model for serviceoriented development. A service component with different communication mechanisms and implementation languages can be modeled in SCA. However, it lacks a formal foundation for SCA-based system specification and verification. This paper presents a formal service component signature model with respect to the specification of the SCA assembly model. Inspired by the idea of independence in SCA, a language-independent dynamic behaviour model is proposed for specifying the interface behaviour of the service component by port activities. Based on the dynamic behaviour model, the compatibility relation between components is discussed. A set of transition rules are given to map Business Process Execution Language for Web Services (BPEL) to dynamic behaviour expressions and then to Petri nets, thus the service component based system can be verified with existing tools. A case study is demonstrated to illustrate how to use our approach to constructing a web application in a rigorous way.

关键词： Service Component Architecture Formal Semantics Service Composition Petri nets Verification

来源：评论

学校读者我要写书评

暂无评论

Hydra: Efficient Detection of Multiple Concurrency Bugs on Fused CPU-GPU Architecture 43

Hydra: Efficient Detection of Multiple Concurrency Bugs on F...

引用

43rd Annual International Conference on parallel Processing (ICPP)

作者： Dai, Zhuofang Wang, Haojun Zhang, Weihua Chen, Haibo Zang, Binyu Fudan Univ Software Sch Shanghai Peoples R China Fudan Univ Shanghai Key Lab Data Sci Shanghai Peoples R China Fudan Univ Parallel Proc Inst Shanghai Peoples R China Shanghai Jiao Tong Univ Inst Parallel & Distributed Syst Shanghai Peoples R China

ISBN: (纸本)9781479956180

Detecting concurrency bugs, such as data race, atomicity violation and order violation, is a cumbersome task for programmers. This situation is further being exacerbated due to the increasing number of cores in a single machine and the prevalence of threaded programming models. Unfortunately, many existing software-based approaches usually incur high runtime overhead or accuracy loss, while most hardware-based proposals usually focus on a specific type of bugs and thus are inflexible to detect a variety of concurrency bugs. In this paper, we propose Hydra, an approach that leverages massive parallelism and programmability of fused GPU architecture to simultaneously detect multiple types of concurrency bugs, including data race, atomicity violation and order violation. Hydra instruments and collects program behavior on CPU and transfers the traces to GPU for bug detection through on-chip interconnect. Furthermore, to achieve high speed, Hydra exploits bloom filter to filter out unnecessary detection traces. Hydra incurs small hardware complexity and requires no changes to internal critical-path processor components such as cache and its coherence protocol, and is with about 1.1% hardware overhead under a 32-core configuration. Experimental results show that Hydra only introduces about 0.35% overhead on average for detecting one type of bugs and 0.92% overhead for simultaneously detecting multiple bugs, yet with the similar detectability of a heavyweight software bug detector (e.g., Helgrind).

关键词： debugging concurrency bug gpu

来源：评论

学校读者我要写书评

暂无评论

High-performance Audio Matching with Features Learned by Convolutional Deep Belief Network 13

High-performance Audio Matching with Features Learned by Con...

引用

13th IEEE International Conference on Signal Processing (ICSP)

作者： Feng, Weijiang Guan, Naiyang Luo, Zhigang Natl Univ Def Technol Coll Comp Inst Software Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Sci & Technol Parallel & Distributed Proc Lab Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781509013456

Audio matching automatically retrieves all excerpts that have the same content as the query audio clip from given audio recordings. The extracted feature is critical for audio matching and the Chroma Energy Normalized Statistics (CENS) feature is the state-of-the-arts. However, CENS might behave unsatisfactorily on some audio because it is a handcraft feature. In this paper, we propose to utilize the features learned by Convolutional Deep Belief Network (CDBN) to enhance the performance of audio matching. Benefit from the strong generalization ability of CDBN, our method works better than CENS based methods on most audio datasets. Since the features learned by CDBN are binary-valued, we can develop a more efficient audio matching algorithm by taking the advantage of this property. Experimental results on both TIMIT dataset and a simulated music dataset confirm effectiveness of the proposed CDBN based method comparing with the traditional CENS feature based algorithm.

关键词： audio matching convolutional deep belief network content-based audio retrieval

来源：评论

学校读者我要写书评

暂无评论

EPP-MVSNet: Epipolar-assembling based Depth Prediction for Multi-view Stereo

EPP-MVSNet: Epipolar-assembling based Depth Prediction for M...

引用

International Conference on Computer Vision (ICCV)

作者： Xinjun Ma Yue Gong Qirui Wang Jingwei Huang Lei Chen Fan Yu Distributed and Parallel Software Lab Huawei Technologies Hong Kong University of Science and Technology

ISBN: (纸本)9781665428132

In this paper, we proposed EPP-MVSNet, a novel deep learning network for 3D reconstruction from multi-view stereo (MVS). EPP-MVSNet can accurately aggregate features at high resolution to a limited cost volume with an optimal depth range, thus, leads to effective and efficient 3D construction. Distinct from existing works which measure feature cost at discrete positions which affects the 3D reconstruction accuracy, EPP-MVSNet introduces an epipolar-assembling-based kernel that operates on adaptive intervals along epipolar lines for making full use of the image resolution. Further, we introduce an entropy-based refining strategy where the cost volume describes the space geometry with the little redundancy. Moreover, we design a light-weighted network with Pseudo-3D convolutions integrated to achieve high accuracy and efficiency. We have conducted extensive experiments on challenging datasets Tanks & Temples(TNT), ETH3D and DTU. As a result, we achieve promising results on all datasets and the highest F-Score on the online TNT intermediate benchmark. Code is available at https://***/mindspore/mindspore/tree/master/model_zoo/research/cv/eppmvsnet.

关键词： Learning systems Costs Three-dimensional displays Image resolution Refining Redundancy Memory management

来源：评论

学校读者我要写书评

暂无评论

A Framework for Recommending Accurate and Diverse Items Using Bayesian Graph Convolutional Neural Networks 20

A Framework for Recommending Accurate and Diverse Items Usin...

引用

26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)

作者： Sun, Jianing Guo, Wei Zhang, Dengcheng Zhang, Yingxue Regol, Florence Hu, Yaochen Guo, Huifeng Tang, Ruiming Yuan, Han He, Xiuqiang Coates, Mark Huawei Noahs Ark Lab Montreal Res Ctr Montreal PQ Canada Huawei Noahs Ark Lab Shenzhen Peoples R China Huawei Distributed & Parallel Software Lab Hangzhou Peoples R China McGill Univ Dept Elect & Comp Engn Montreal PQ Canada

ISBN: (纸本)9781450379984

Personalized recommender systems are playing an increasingly important role for online consumption platforms. Because of the multitude of relationships existing in recommender systems, Graph Neural Networks (GNNs) based approaches have been proposed to better characterize the various relationships between a user and items while modeling a user's preferences. Previous graph-based recommendation approaches process the observed user-item interaction graph as a ground-truth depiction of the relationships between users and items. However, especially in the implicit recommendation setting, all the unobserved user-item interactions are usually assumed to be negative samples. There are missing links that represent a user's future actions. In addition, there may be spurious or misleading positive interactions. To alleviate the above issue, in this work, we take a first step to introduce a principled way to model the uncertainty in the user-item interaction graph using the Bayesian Graph Convolutional Neural Network framework. We discuss how inference can be performed under our framework and provide a concrete formulation using the Bayesian Probabilistic Ranking training loss. We demonstrate the effectiveness of our proposed framework on four benchmark recommendation datasets. The proposed method outperforms state-of-the-art graph-based recommendation models. Furthermore, we conducted an offline evaluation on one industrial large-scale dataset. It shows that our proposed method outperforms the baselines, with the potential gain being more significant for cold-start users. This illustrates the potential practical benefit in real-world recommender systems.

关键词： Graph Convolution Networks Recommendation Collaborative Filtering Bayesian Graph Neural Networks

来源：评论

学校读者我要写书评

暂无评论

IS-MVSNet:Importance Sampling-Based MVSNet 17th

IS-MVSNet:Importance Sampling-Based MVSNet

引用

17th European Conference on Computer Vision (ECCV)

作者： Wang, Likang Gong, Yue Ma, Xinjun Wang, Qirui Zhou, Kaixuan Chen, Lei Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Clear Water Bay Hong Kong Peoples R China Huawei Technol Distributed & Parallel Software Lab Shenzhen Peoples R China Huawei Technol Riemann Lab Shenzhen Peoples R China Huawei Technol Fundamental Software Innovat Lab Shenzhen Peoples R China

ISBN: (纸本)9783031198236;9783031198243

This paper presents a novel coarse-to-fine multi-view stereo (MVS) algorithm called importance-sampling-based MVSNet (IS-MVSNet) to address a crucial problem of limited depth resolution adopted by current learning-based MVS methods. We proposed an importance-sampling module for sampling candidate depth, effectively achieving higher depth resolution and yielding better point-cloud results while introducing no additional cost. Furthermore, we proposed an unsupervised error distribution estimation method for adjusting the density variation of the importance-sampling module. Notably, the proposed sampling module does not require any additional training and works reasonably well with the pre-trained weights of the baseline model. Our proposed method leads to up to 20x promotion on the most refined depth resolution, thus significantly benefiting most scenarios and excellently superior on fine details. As a result, IS-MVSNet outperforms all the published papers on TNT's intermediate benchmark with an F-score of 62.82%. Code is available at ***/NoOneUST/IS-MVSNet.

关键词： 3D reconstruction Multi-view stereo Importance sampling

来源：评论

学校读者我要写书评

暂无评论

WPress: An Application-Driven Performance Benchmark For Cloud-Based Virtual Machines 18

WPress: An Application-Driven Performance Benchmark For Clou...

引用

18th IEEE International Enterprise distributed Object Computing Conference (EDOC)

作者： Borhani, Amir Hossein Leitner, Philipp Lee, Bu-Sung Li, Xiaorong Hung, Terence Inst High Performance Comp Singapore 13863 Singapore Univ Zurich Seal Software Evolut & Architecture Lab CH-8006 Zurich Switzerland Nanyang Technol Univ Sch Comp Engn Parallel & Distributed Comp Ctr Singapore 639798 Singapore

ISBN: (纸本)9781479954704

Approaching a comprehensive performance benchmark for on-line transaction processing (OLTP) applications in a cloud environment is a challenging task. Fundamental features of clouds, such as the pay-as-you-go pricing model and unknown underlying configuration of the system, are contrary to the basic assumptions of available benchmarks such as TPC-W or RUBiS. In this paper, we introduce a systematic performance benchmark approach for OLTP applications on public clouds that use virtual machines (VMs). We propose WPress benchmark, which is based on the widespread blogging software, WordPress, as a representative OLTP application and implement an open source workload generator. Furthermore, we utilize a CPU micro-benchmark to investigate CPU performance of cloud-based VMs in greater detail. Average response time and total VM cost are the performance metrics measured by WPress. We evaluate small and large instance types of three real-life cloud providers, Amazon EC2, Microsoft Azure and Rackspace cloud. Results imply that Rackspace cloud has better average response times and total VM cost on small instances. However, Microsoft Azure is preferable for large instance type.

关键词： Benchmarking Cloud Computing Virtual Machine Amazon EC2 Microsoft Azure Rackspace Cloud OLTP CPU Micro-Benchmark

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：