检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xiao, Mingqing Meng, Qingyan Zhang, Zongpeng He, Di Lin, Zhouchen National Key Lab of General AI School of Intelligence Science and Technology Peking University China The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data China Department of Biostatistics School of Public Health Peking University China Institute for Artificial Intelligence Peking University China Peng Cheng Laboratory China

Neuromorphic computing with spiking neural networks is promising for energy-efficient artificial intelligence (AI) applications. However, different from humans who continually learn different tasks in a lifetime, neural network models suffer from catastrophic forgetting. How could neuronal operations solve this problem is an important question for AI and neuroscience. Many previous studies draw inspiration from observed neuroscience phenomena and propose episodic replay or synaptic metaplasticity, but they are not guaranteed to explicitly preserve knowledge for neuron populations. Other works focus on machine learning methods with more mathematical grounding, e.g., orthogonal projection on high dimensional spaces, but there is no neural correspondence for neuromorphic computing. In this work, we develop a new method with neuronal operations based on lateral connections and Hebbian learning, which can protect knowledge by projecting activity traces of neurons into an orthogonal subspace so that synaptic weight update will not interfere with old tasks. We show that Hebbian and anti-Hebbian learning on recurrent lateral connections can effectively extract the principal subspace of neural activities and enable orthogonal projection. This provides new insights into how neural circuits and Hebbian learning can help continual learning, and also how the concept of orthogonal projection can be realized in neuronal systems. Our method is also flexible to utilize arbitrary training methods based on presynaptic activities/traces. Experiments show that our method consistently solves forgetting for spiking neural networks with nearly zero forgetting under various supervised training methods with different error propagation approaches, and outperforms previous approaches under various settings. Our method can pave a solid path for building continual neuromorphic computing systems. The code is available at https://***/pkuxmq/HLOP-SNN. © 2024, CC BY-NC-SA.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

FlashWalker: An In-Storage Accelerator for Graph Random Walks

FlashWalker: An In-Storage Accelerator for Graph Random Walk...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Fuping Niu Jianhui Yue Jiangqiu Shen Xiaofei Liao Haikun Liu Hai Jin National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Computer Science Michigan Technological University Houghton Michigan USA

Graph random walk is widely used in the graph processing as it is a fundamental component in graph analysis, ranging from vertices ranking to the graph embedding. Different from traditional graph processing workload, random walk features massive processing parallelisms and poor graph data reuse, being limited by low I/O efficiency. Prior designs for random walk mitigate slow I/O operations. However, the state-of-the-art random walk processing systems are bounded by slow disk I/O bandwidth, which is confirmed by our experiments with real-world graphs. To address this issue, we propose FlashWalker, an in-storage accelerator for random walk that moves walk updating close to graph data stored in flash memory, by exploiting significant parallelisms inside SSD. Featuring a heterogeneous and parallel processing system, FlashWalker includes a board-level accelerator, channel-level accelerators, and chip-level accelerators. To address challenges posed by the tight resource constraints for processing large-scale graphs, we propose novel designs: storing a few popular subgraphs in accelerators, the pre-walking for dense walks, two optimizations to search the subgraph mapping table, and a subgraph scheduling algorithm. We implement FlashWalker in RTL, showing small circuit area overhead. Our evaluation shows FlashWalker reduces the execution time of random walk algorithms by up to 660.50×, compared with GraphWalker, which is the state-of-the-art system for random walk algorithms.

关键词： Distributed processing Scheduling algorithms Bandwidth Parallel processing Distance measurement Flash memories Optimization

来源：评论

学校读者我要写书评

暂无评论

Research on the Influencing Factors of Brand Diffusion via Social Media

Research on the Influencing Factors of Brand Diffusion via S...

引用

2020 International Conference on Agricultural science and Technology and Food Engineering, ASTFE 2020

作者： Yunan, Peng Zongshui, Wang Jian, Zhang School of Economics and Management Information Science and Technology University Beijing China Beijing Key Lab of Green Development and Decision Based on Big Data China

[Purpose] The paper aims to identify the impact factors of brand diffusion via social media. It provides a theoretical reference for enterprises to choose social media and improves brand influence. [Method] First, we summarize the general path of brand diffusion through social media by studying the relevant literatures. Next, four popular social media WeChat, Weibo, Tiktok, and Taobao have been selected as research samples to analyze the different brand diffusion paths. Finally, we summarize the impact of brand diffusion on social media according to the paths. [Results] The result shows that the main factors influencing brand diffusion on social media are diffusion content, information credibility, audience participation, and diffusion path. © The Authors, published by EDP sciences, 2020.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Embedding Dynamic Attributed Networks by Modeling the Evolution Processes 28

Embedding Dynamic Attributed Networks by Modeling the Evolut...

引用

28th International Conference on Computational Linguistics, COLING 2020

作者： Xu, Zenan Ou, Zijing Su, Qinliang Yu, Jianxing Quan, Xiaojun Lin, Zhenkun School of Data and Computer Science Sun Yat-Sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781952148279

Network embedding has recently emerged as a promising technique to embed nodes of a network into low-dimensional vectors. While fairly successful, most existing works focus on the embedding techniques for static networks. But in practice, there are many networks that are evolving over time and hence are dynamic, e.g., the social networks. To address this issue, a high-order spatio-temporal embedding model is developed to track the evolutions of dynamic networks. Specifically, an activeness-aware neighborhood embedding method is first proposed to extract the high-order neighborhood information at each given timestamp. Then, an embedding prediction framework is further developed to capture the temporal correlations, in which the attention mechanism is employed instead of recurrent neural networks (RNNs) for its efficiency in computing and flexibility in modeling. Extensive experiments are conducted on four real-world datasets from three different areas. It is shown that the proposed method outperforms all the baselines by a substantial margin for the tasks of dynamic link prediction and node classification, which demonstrates the effectiveness of the proposed methods on tracking the evolutions of dynamic networks. © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits

arXiv

引用

arXiv 2021年

作者： Bai, Jiawang Wu, Baoyuan Zhang, Yong Li, Yiming Li, Zhifeng Xia, Shu-Tao Tsinghua Shenzhen International Graduate School Tsinghua University China PCL Research Center of Networks and Communications Peng Cheng Laboratory China School of Data Science The Chinese University of Hong Kong Shenzhen China Secure Computing Lab of Big Data Shenzhen Research Institute of Big Data China Tencent AI Lab United States

To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the adversarial attack in the inference stage. In this paper, we study a novel attack paradigm, which modifies model parameters in the deployment stage for malicious purposes. Specifically, our goal is to misclassify a specific sample into a target class without any sample modification, while not significantly reduce the prediction accuracy of other samples to ensure the stealthiness. To this end, we formulate this problem as a binary integer programming (BIP), since the parameters are stored as binary bits (i.e., 0 and 1) in the memory. By utilizing the latest technique in integer programming, we equivalently reformulate this BIP problem as a continuous optimization problem, which can be effectively and efficiently solved using the alternating direction method of multipliers (ADMM) method. Consequently, the flipped critical bits can be easily determined through optimization, rather than using a heuristic strategy. Extensive experiments demonstrate the superiority of our method in attacking DNNs. The code is available at: https://***/jiawangbai/TA-LBF. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Wound Tissue Segmentation in Diabetic Foot Ulcer Images Using Deep Learning: A Pilot Study

arXiv

引用

arXiv 2024年

作者： Dhar, Mrinal Kanti Wang, Chuanbo Patel, Yash Zhang, Taiyu Niezgoda, Jeffrey Gopalakrishnan, Sandeep Chen, Keke Yu, Zeyun Big Data Analytics and Visualization Lab Department of Computer Science University of Wisconsin-Milwaukee MilwaukeeWI United States Auxillium Health MilwaukeeWI United States Wound Healing and Tissue Repair Analytics Laboratory School of Biomedical Sciences & Health Care Administration University of Wisconsin Milwaukee MilwaukeeWI United States Department of Computer Science Marquette University MilwaukeeWI United States

Identifying individual tissues, so-called tissue segmentation, in diabetic foot ulcer (DFU) images is a challenging task and little work has been published, largely due to the limited availability of a clinical image dataset. To address this gap, we have created a DFUTissue dataset for the research community to evaluate wound tissue segmentation algorithms. The dataset contains 110 images with tissues labeled by wound experts and 600 unlabeled images. Additionally, we conducted a pilot study on segmenting wound characteristics including fibrin, granulation, and callus using deep learning. Due to the limited amount of annotated data, our framework consists of both supervised learning (SL) and semi-supervised learning (SSL) phases. In the SL phase, we propose a hybrid model featuring a Mix Transformer (MiT-b3) in the encoder and a CNN in the decoder, enhanced by the integration of a parallel spatial and channel squeeze- and-excitation (P-scSE) module known for its efficacy in improving boundary accuracy. The SSL phase employs a pseudo-labeling-based approach, iteratively identifying and incorporating valuable unlabeled images to enhance overall segmentation performance. Comparative evaluations with state-of-the-art methods are conducted for both SL and SSL phases. The SL achieves a Dice Similarity Coefficient (DSC) of 84.89%, which has been improved to 87.64% in the SSL phase. Furthermore, the results are benchmarked against two widely used SSL approaches—Generative Adversarial Networks and Cross-Consistency Training. Additionally, our hybrid model outperforms the state-of-the-art methods with a 92.99% DSC in performing binary segmentation of DFU wound areas when tested on the Chronic Wound dataset. Codes and data are available at https://***/uwm-bigdata/DFUTissueSegNet. © 2024, CC BY-NC-SA.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Takeover Performance and Workload under Varying Automation Levels, Time Budget and Road Curvature

Takeover Performance and Workload under Varying Automation L...

引用

2022 IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2022

作者： Xu, Chengliang Li, Penghui Li, Yibing Merat, Natasha Lu, Ziwang Guo, Xing Tsinghua University State Key Laboratory of Automotive Safety and Energy School of Vehicle and Mobility Beijing China Beijing Jiaotong University Key Lab. of Transport Industry of Big Data Application Technologies for Comprehensive Transport School of Traffic and Transportation Beijing China University of Leeds Institute for Transport Studies Leeds United Kingdom Beijing Information Science and Technology University School of Mechanical and Electrical Engineering Beijing China

ISBN: (纸本)9781665409025

In SAE Level 2 (L2) and Level 3 (L3) automated driving, drivers are required to take over control from automation when reaching system boundaries. The length of time budget is the vital parameter that needs to be determined to ensure a safe takeover manner. Existing literature on this issue rarely considers potential interactions between time budget and other factors, and a variable time budget seemed to be paradoxical in critical unplanned transitions. To this end, this study investigated drivers' takeover performance and workload under varying automation levels, time budget and road curvature. We employed the operational design domain (ODD) exiting event as the transition scenario where the ego car was about to leave the highway. Results showed that drivers in L3 takeovers performed worse and elicited higher workload than L2 when entering a curved ramp with a limited time budget. Takeovers when entering a curved ramp yielded worse performance and higher workload, as compared to entering a straight ramp. Such detrimental effects caused by loss of situation awareness (SA) and change of road curvature can be mitigated by increasing the length of time budget. All these findings suggest that even in simplified ODD exiting scenarios, the length of time budget should vary according to the state of the driver and the environment. © 2022 IEEE.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Contrastive Multi-view Hyperbolic Hierarchical Clustering

arXiv

引用

arXiv 2022年

作者： Lin, Fangfei Bai, Bing Bai, Kun Ren, Yazhou Zhao, Peng Xu, Zenglin University of Electronic Science and Technology of China Chengdu China Tencent Security Big Data Lab Tencent Inc. China Harbin Institute of Technology Shenzhen China Department of Network Intelligence Peng Cheng National Lab Shenzhen China

Hierarchical clustering recursively partitions data at an increasingly finer granularity. In real-world applications, multi-view data have become increasingly important. This raises a less investigated problem, i.e., multi-view hierarchical clustering, to better understand the hierarchical structure of multi-view data. To this end, we propose a novel neural network-based model, namely Contrastive Multi-view Hyperbolic Hierarchical Clustering (CMHHC). It consists of three components, i.e., multi-view alignment learning, aligned feature similarity learning, and continuous hyperbolic hierarchical clustering. First, we align sample-level representations across multiple views in a contrastive way to capture the view-invariance information. Next, we utilize both the manifold and Euclidean similarities to improve the metric property. Then, we embed the representations into a hyperbolic space and optimize the hyperbolic embeddings via a continuous relaxation of hierarchical clustering loss. Finally, a binary clustering tree is decoded from optimized hyperbolic embeddings. Experimental results on five real-world datasets demonstrate the effectiveness of the proposed method and its components. Copyright © 2022, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

An Efficient Block Validation Mechanism for UTXO-based Blockchains

An Efficient Block Validation Mechanism for UTXO-based Block...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Xiaohai Dai Bin Xiao Jiang Xiao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing The Hong Kong Polytechnic University Hong Kong

It has been recognized that one of the bottlenecks in the UTXO-based blockchain systems is the slow block validation - the process of validating a newly-received block by a node before locally storing it and further broadcasting it. As a block contains multiple inputs, the block validation mainly involves checking the inputs against the status data, which is also known as the Unspent Transaction Outputs (UTXO) set. As time goes by, the UTXO set becomes more and more expansive, most of which can only be stored on disks. This considerably slows down the input checking and thus block validation, which can potentially compromise system security. To deal with the above problem, we disassemble the function of input checking into three parts: existence validation (EV), unspent validation (UV), and script validation (SV). Based on the disassembly, we propose EBV, an efficient block validation mechanism to speed up EV, UV, and SV individually. First, EBV changes the representation of status data, from UTXO set to a bit-vector set, which drastically reduces its size. The smaller status data can be entirely maintained in memory, thereby accelerating UV and also block validation. Second, EBV requires each transaction to carry the proof data, which enables EV and SV without accessing the disks. Furthermore, we also cope with two challenges in the design of EBV, namely transaction inflation and fake positions. To evaluate the EBV mechanism, we implement a prototype on top of Bitcoin, the most widely known UTXO-based blockchain, and conduct extensive experiments to compare EBV and Bitcoin. The experimental results demonstrate that EBV successfully reduces the memory requirement by 93.1 % and the block validation time by up to 93.5%.

关键词： Distributed processing Memory management Prototypes Bitcoin Broadcasting Blockchains Delays

来源：评论

学校读者我要写书评

暂无评论

BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean label

arXiv

引用

arXiv 2022年

作者： Hu, Shengshan Zhou, Ziqi Zhang, Yechao Zhang, Leo Yu Zheng, Yifeng He, Yuanyuan Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China School of Information Technology Deakin University VIC3216 Australia School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security HUST Wuhan430074 China Cluster and Grid Computing Lab HUST Wuhan430074 China

Due to its powerful feature learning capability and high efficiency, deep hashing has achieved great success in large-scale image retrieval. Meanwhile, extensive works have demonstrated that deep neural networks (DNNs) are susceptible to adversarial examples, and exploring adversarial attack against deep hashing has attracted many research efforts. Nevertheless, backdoor attack, another famous threat to DNNs, has not been studied for deep hashing yet. Although various backdoor attacks have been proposed in the field of image classification, existing approaches failed to realize a truly imperceptive backdoor attack that enjoys invisible triggers and clean label setting simultaneously, and they also cannot meet the intrinsic demand of image retrieval backdoor. In this paper, we propose BadHash, the first generative-based imperceptible backdoor attack against deep hashing, which can effectively generate invisible and input-specific poisoned images with clean label. Specifically, we first propose a new conditional generative adversarial network (cGAN) pipeline to effectively generate poisoned samples. For any given benign image, it seeks to generate a natural-looking poisoned counterpart with a unique invisible trigger. In order to improve the attack effectiveness, we introduce a label-based contrastive learning network labCLN to exploit the semantic characteristics of different labels, which are subsequently used for confusing and misleading the target model to learn the embedded trigger. We finally explore the mechanism of backdoor attacks on image retrieval in the hash space. Extensive experiments on multiple benchmark datasets verify that BadHash can generate imperceptible poisoned samples with strong attack ability and transferability over state-of-the-art deep hashing schemes. © 2022, CC BY.

关键词： Deep neural networks

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：