检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ma, Chenxiang Chen, Xinyi Li, Yanchen Yang, Qu Wu, Yujie Li, Guoqi Pan, Gang Tang, Huajin Tan, Kay Chen Wu, Jibin Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong Department of Computing The Hong Kong Polytechnic University Hong Kong Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore Institute of Automation Chinese Academy of Sciences Beijing100045 China State Key Laboratory of Brain-Machine Intelligence College of Computer Science and Technology MOE Frontier Science Center for Brain Science and Brain-Machine Integration Zhejiang University Hangzhou310027 China

Temporal processing is fundamental for both biological and artificial intelligence systems, as it enables the comprehension of dynamic environments and facilitates timely responses. Spiking Neural Networks (SNNs) excel in handling such data with high efficiency, owing to their rich neuronal dynamics and sparse activity patterns. Given the recent surge in the development of SNNs, there is an urgent need for a comprehensive evaluation of their temporal processing capabilities. In this paper, we first conduct an in-depth assessment of commonly used neuromorphic benchmarks, revealing critical limitations in their ability to evaluate the temporal processing capabilities of SNNs. To bridge this gap, we further introduce a benchmark suite consisting of three temporal processing tasks characterized by rich temporal dynamics across multiple timescales. Utilizing this benchmark suite, we perform a thorough evaluation of recently introduced SNN approaches to elucidate the current status of SNNs in temporal processing. Our findings indicate significant advancements in recently developed spiking neuron models and neural architectures regarding their temporal processing capabilities, while also highlighting a performance gap in handling long-range dependencies when compared to state-of-the-art non-spiking models. Finally, we discuss the key challenges and outline potential avenues for future research. Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Regression with Phrase Indicators for Estimating MT Quality 7

Regression with Phrase Indicators for Estimating MT Quality

引用

7th Workshop on Statistical machine Translation, WMT 2012, immediately following the Conference of the North-American Chapter of the Association for Computational Linguistics - Human Language Technologies, NAACL HLT 2012

作者： Wu, Chunyang Zhao, Hai Department Of Computer Science And Engineering Center For Brain-Like Computing And Machine Intelligence Shanghai Jiao Tong University China

ISBN: (纸本)9781937284206

We in this paper describe the regression system for our participation in the quality estimation task of WMT12. This paper focuses on exploiting special phrases, or word sequences, to estimate translation quality. Several feature templates on this topic are put forward subsequently. We train a SVM regression model for predicting the scores and numerical results show the effectiveness of our phrase indicators and method in both ranking and scoring tasks. ©2012 Association for Computational Linguistics.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Human parsing with edge enhancement

Human parsing with edge enhancement

引用

2021 IEEE International Conference on Real-Time computing and Robotics, RCAR 2021

作者： Ma, Lei Wang, Jian Shao, Jie Zhang, Liqing Center for Brain-like Computing and Machine Intelligence Shanghai Jiao Tong University Shanghai China AI Lab ByteDance Inc. Shanghai China

ISBN: (纸本)9781665436786

Human parsing, which aims at segmenting human images according to body parts, attracts many researchers' attention because of its various application perspectives. The problem requires accurate object edge detection on segmentation masks. However, the edge information has not been fully explored in the existing methods for this issue. This paper focuses on enhancing body's edge segmentation performance of the human parsing problem. The proposed enhancement method includes three aspects, which are feature extraction, context information, and edge refinement. To this end, we introduce an edge enhancement module that focuses on edge enhancement and refines the object edges from a coarse predicted segmentation mask. The edge enhancement module, together with a context embedding module and a feature extraction module, is integrated into a state-of-the-art human parsing framework. Our proposed method can significantly improve the performance in edge estimation. The experimental results on LIP dataset and PASCAL-Person-Part dataset validate the excellent performance of our method. © 2021 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

SpikingMiniLM: energy-efficient spiking transformer for natural language understanding

引用

Science China(Information Sciences) 2024年第10期67卷 115-128页

作者： Jiayu ZHANG Jiangrong SHEN Zeke WANG Qinghai GUO Rui YAN Gang PAN Huajin TANG College of Computer Science and Technology Zhejiang University The State Key Lab of Brain-Machine Intelligence Zhejiang University Collaborative Innovation Center of Artificial Intelligence Zhejiang University Advanced Computing and Storage Laboratory Huawei Technologies Co. Ltd. College of Computer Science and Technology Zhejiang University of Technology MOE Frontier Science Center for Brain Science and Brain-Machine Integration Zhejiang University

In the era of large-scale pretrained models, artificial neural networks（ANNs） have excelled in natural language understanding（NLU） tasks. However, their success often necessitates substantial computational resources and energy consumption. To address this, we explore the potential of spiking neural networks（SNNs） in NLU——a promising avenue with demonstrated advantages, including reduced power consumption and improved efficiency due to their event-driven characteristics. We propose the SpikingMiniLM,a novel spiking Transformer model tailored for natural language understanding. We first introduce a multi-step encoding method to convert text embeddings into spike trains. Subsequently, we redesign the attention mechanism and residual connections to make our model operate on the pure spike-based paradigm without any normalization technique. To facilitate stable and fast convergence, we propose a general parameter initialization method grounded in the stable firing rate principle. Furthermore, we apply an ANN-to-SNN knowledge distillation to overcome the challenges of pretraining SNNs. Our approach achieves a macro-average score of 75.5 on the dev sets of the GLUE benchmark, retaining 98% of the performance exhibited by the teacher model MiniLMv2. Our smaller model also achieves similar performance to BERTMINIwith fewer parameters and much lower energy consumption, underscoring its competitiveness and resource efficiency in NLU tasks.

关键词： spiking neural networks natural language understanding spiking Transformer spike-based attention multi-step encoding ANN-to-SNN distillation

来源：评论

学校读者我要写书评

暂无评论

Learning from imbalanced data sets with a Min-Max modular support vector machine

引用

中国电气与电子工程前沿 2011年第1期6卷 56-71页

作者： Bao-Liang LU Xiao-Lin WANG Yang YANG Hai ZHAO Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and EngineeringShanghai Jiao Tong UniversityShanghai 200240China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong UniversityShanghai 200240China Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and EngineeringShanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Engineering Shanghai Maritime UniversityShanghai 201306China

Imbalanced data sets have significantly unequal distributions between *** between-class imbalance causes conventional classification methods to favor majority classes,resulting in very low or even nO detection of minority classes.A Min-Max modular support vector machine(M3-SVM)approaches this problem by decomposing the training input sets of the majority classes into subsets of similar size and pairing them into balanced two-class classification *** approach has the merits of using general classifiers,incorporating prior knowledge into task decomposition and parallel *** on two real-world pattern classification problems,international patent classification and protein subcellar localization,demonstrate the effectiveness of the proposed approach.

关键词： imbalanced data Min-Max modular network(M3-network) prior knowledge parallel learning support vector machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

machine translation approach for Chinese whole-sentence Pinyin-to-character conversion

Machine translation approach for Chinese whole-sentence Piny...

引用

26th Pacific Asia Conference on Language, Information and Computation, PACLIC 2012

作者： Yang, Shaohua Zhao, Hai Lu, Bao-Liang MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Center for Brain-Like Computing and Machine Intelligence Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China

ISBN: (纸本)9789791421171

This paper introduces a new approach to solve the Chinese Pinyin-to-character (PTC) conversion problem. The conversion from Chinese Pinyin to Chinese character can be regarded as a transformation between two different languages (from the Latin writing system of Chinese Pinyin to the character form of Chinese,Hanzi), which can be naturally solved by machine translation framework. PTC problem is usually regarded as a sequence labeling problem, however, it is more difficult than any other general sequence labeling problems, since it requires a large label set of all Chinese characters for the labeling task. The essential difficulty of the task lies in the high degree of ambiguities of Chinese characters corresponding to Pinyins. Our approach is novel in that it effectively combines the features of continuous source sequence and target sequence. The experimental results show that the proposed approach is much faster, besides, we got a better result and outperformed the existing sequence labeling approaches. © 2012 The PACLIC.

关键词： machine translation

来源：评论

学校读者我要写书评

暂无评论

Flatten hierarchies for large-scale hierarchical text categorization

Flatten hierarchies for large-scale hierarchical text catego...

引用

International Conference on Digital Information Management

作者： Wang, Xiao-Lin Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University China

ISBN: (纸本)9781424475728

Hierarchies are very popular in organizing documents and web pages, hence automated hierarchical classification techniques are desired. However, the current dominant hierarchical approach of top-down method suffers accuracy decrease compared with flat classification approaches, because of error propagation and bottom nodes' data sparsity. In this paper we flatten hierarchies to relieve such accuracy decrease in top-down method, which aims to make hierarchies both effective enough to make large-scale classification tasks feasible, and simple enough to ensure high classification accuracy. We propose two flattening strategies based on these two causes of the accuracy decrease, and experimental results show that the flattening strategy designed for error propagation is more effective, which suggests that hierarchies with lots of branches at top layers can provide high classification accuracy. Besides, we analyze the computational complexity before and after flattening, which approximately agree with the experimental results. ©2010 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

KySS 1.0: a Framework for Automatic Evaluation of Chinese Input Method Engines 6

KySS 1.0: a Framework for Automatic Evaluation of Chinese In...

引用

6th International Joint Conference on Natural Language Processing, IJCNLP 2013

作者： Jia, Zhongye Zhao, Hai MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China

ISBN: (纸本)9784990734800

Chinese Input Method Engine (IME) plays an important role in Chinese language processing. However, it has been subjected to lacking a proper evaluation metric for a long time. The natural metric for IME is user experience, which is a rather vague goal for research purpose. We propose a novel approach of quantifying user experience by using keystroke count and then correspondingly develop a framework of IME evaluation, which is fast and accurate. With the underlying linguistic background, the proposed evaluation framework can properly model the user behavior as Chinese is input through English keyboard. It is helpful to point out a way to improve the current Chinese IME performance. © IJCNLP *** right reserved.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

Chinese coreference resolution via ordered filtering

Chinese coreference resolution via ordered filtering

引用

2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012 - Shared Task: Modeling Multilingual Unrestricted Coreference in OntoNotes

作者： Zhang, Xiaotian Wu, Chunyang Zhao, Hai Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University China

ISBN: (纸本)9781937284459

We in this paper present the model for our participation (BCMI) in the CoNLL-2012 Shared Task. This paper describes a pure rule-based method, which assembles different filters in a proper order. Different filters handle different situations and the filtering strategies are designed manually. These filters are assigned to different ordered tiers from general to special cases. We participated in the Chinese and English closed tracks, scored 51.83 and 59.24 respectively. © 2012 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Grammatical error correction as multiclass classification with single model 17

Grammatical error correction as multiclass classification wi...

引用

17th Conference on Computational Natural Language Learning: Shared Task, CoNLL 2013

作者： Jia, Zhongye Wang, Peilu Zhao, Hai MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China

ISBN: (纸本)9781937284718

This paper describes our system in the shared task of CoNLL-2013. We illustrate that grammatical error detection and correction can be transformed into a multiclass classification task and implemented as a single-model system regardless of various error types with the aid of maximum entropy modeling. Our system achieves the F1 score of 17.13% on the standard test set. © 2013 Association for Computational Linguistics.

关键词： Error correction

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：