检索结果-内蒙古大学图书馆

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Jiang, Xiaoze Yu, Jing Sun, Yajing Qin, Zengchang Zhu, Zihao Hu, Yue Wu, Qi Institute of Information Engineering Chinese Academy of Sciences Beijing China Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China AI Research Codemao Inc University of Adelaide Australia

ISBN: (纸本)9780999241165

Visual Dialogue task requires an agent to be engaged in a conversation with human about an image. The ability of generating detailed and non-repetitive responses is crucial for the agent to achieve human-like conversation. In this paper, we propose a novel generative decoding architecture to generate high-quality responses, which moves away from decoding the whole encoded semantics towards the design that advocates both transparency and flexibility. In this architecture, word generation is decomposed into a series of attention-based information selection steps, performed by the novel recurrent Deliberation, Abandon and Memory (DAM) module. Each DAM module performs an adaptive combination of the response-level semantics captured from the encoder and the word-level semantics specifically selected for generating each word. Therefore, the responses contain more detailed and non-repetitive descriptions while maintaining the semantic accuracy. Furthermore, DAM is flexible to cooperate with existing visual dialogue encoders and adaptive to the encoder structures by constraining the information selection mode in DAM. We apply DAM to three typical encoders and verify the performance on the VisDial v1.0 dataset. Experimental results show that the proposed models achieve new state-of-the-art performance with high-quality responses. The code is available at https://***/JXZe/DAM. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-View Document Representation learning for Open-Domain Dense Retrieval

arXiv

引用

arXiv 2022年

作者： Zhang, Shunyu Liang, Yaobo Gong, Ming Jiang, Daxin Duan, Nan Intelligent Computing and Machine Learning Lab School of ASEE Beihang University China Microsoft Research Asia China Microsoft STC Asia

Dense retrieval has achieved impressive advances in first-stage retrieval from a large-scale document collection, which is built on bi-encoder architecture to produce single vector representation of query and document. However, a document can usually answer multiple potential queries from different views. So the single vector representation of a document is hard to match with multi-view queries, and faces a semantic mismatch problem. This paper proposes a multi-view document representation learning framework, aiming to produce multi-view embeddings to represent documents and enforce them to align with different queries. First, we propose a simple yet effective method of generating multiple embeddings through viewers. Second, to prevent multi-view embeddings from collapsing to the same one, we further propose a global-local loss with annealed temperature to encourage the multiple viewers to better align with different potential queries. Experiments show our method outperforms recent works and achieves state-of-the-art results. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient 41

Double Variance Reduction: A Smoothing Trick for Composite O...

引用

41st International Conference on machine learning, ICML 2024

作者： Di, Hao Ye, Haishan Zhang, Yueling Chang, Xiangyu Dai, Guang Tsang, Ivor W. Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China China International Business School Beijing Foreign Studies University Beijing China Singapore College of Computing and Data Science NTU Singapore

Variance reduction techniques are designed to decrease the sampling variance, thereby accelerating convergence rates of first-order (FO) and zeroth-order (ZO) optimization methods. However, in composite optimization problems, ZO methods encounter an additional variance called the coordinate-wise variance, which stems from the random gradient estimation. To reduce this variance, prior works require estimating all partial derivatives, essentially approximating FO information. This approach demands O(d) function evaluations (d is the dimension size), which incurs substantial computational costs and is prohibitive in high-dimensional scenarios. This paper proposes the Zeroth-order Proximal Double Variance Reduction (ZPDVR) method, which utilizes the averaging trick to reduce both sampling and coordinate-wise variances. Compared to prior methods, ZPDVR relies solely on random gradient estimates, calls the stochastic zeroth-order oracle (SZO) in expectation O(1) times per iteration, and achieves the optimal O(d(n+κ) log(1/ϵ)) SZO query complexity in the strongly convex and smooth setting, where κ represents the condition number and ϵ is the desired accuracy. Empirical results validate ZPDVR's linear convergence and demonstrate its superior performance over other related methods. Copyright 2024 by the author(s)

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering

arXiv

引用

arXiv 2018年

作者： Yang, Zhuoqian Qin, Zengchang Yu, Jing Hu, Yue Intelligent Computing and Machine Learning Lab School of Automation Science and Electrical Engineering Beihang University Institute of Information Engineering Chinese Academy of Sciences

One of the key issues of Visual Question Answering (VQA) is to reason with semantic clues in the visual content under the guidance of the question, how to model relational semantics still remains as a great challenge. To fully capture visual semantics, we propose to reason over a structured visual representation – scene graph, with embedded objects and inter-object relationships. This shows great benefit over vanilla vector representations and implicit visual relationship learning. Based on existing visual relationship models, we propose a visual relationship encoder that projects visual relationships into a learned deep semantic space constrained by visual context and language priors. Upon the constructed graph, we propose a Scene Graph Convolutional Network (SceneGCN) to jointly reason the object properties and relational semantics for the correct answer. We demonstrate the model’s effectiveness and interpretability on the challenging GQA dataset and the classical VQA 2.0 dataset, remarkably achieving state-of-the-art 54.56% accuracy on GQA compared to the existing best model. Copyright © 2018, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A new technique for summarizing video sequences through histogram evolution

A new technique for summarizing video sequences through hist...

引用

International Conference on Signal Processing and Communications, SPCOM

作者： Tao Wan Zengchang Qin College of Information Science and Technology Beijing Normal University Beijing China Intelligent Computing and Machine Learning Lab Beihang University Beijing China

We present an efficient technique based on histogram evolution for summarizing video sequences to make them more amenable to browsing and retrieval. First, a ground-truth database of videos is generated in which the shot breaks are detected by human subjects and numbered in order. Three types of histogram are then used to capture the characteristics of color content containing in the video frames. The principle components analysis (PCA) method is adopted to reduce the histogram dimensions and form a 2D feature space. Finally, two approaches, frame difference measures and Fuzzy C-means clustering, are employed to extract video shot breaks. Polylines are drawn between the detected shot breaks to show that the histogram of their colors evolves from frame to frame. In comparison with the ground-truth database, the proposed algorithm achieves a surprising high detection accuracy rate. The extensive experiments also demonstrate that the patterns of histogram evolution can be useful to identify the shot break types, such as cut, dissolve, fade-out, fade-in, and wipe.

关键词： Histograms Video sequences Image color analysis Gray-scale Databases Humans Clustering methods

来源：评论

学校读者我要写书评

暂无评论

Sparse Double Descent: Where Network Pruning Aggravates Overfitting

arXiv

引用

arXiv 2022年

作者： He, Zheng Xie, Zeke Zhu, Quanzhi Qin, Zengchang Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing China The University of Tokyo Japan RIKEN Center for AIP Japan

People usually believe that network pruning not only reduces the computational cost of deep networks, but also prevents overfitting by decreasing model capacity. However, our work surprisingly discovers that network pruning sometimes even aggravates overfitting. We report an unexpected sparse double descent phenomenon that, as we increase model sparsity via network pruning, test performance first gets worse (due to overfitting), then gets better (due to relieved overfitting), and gets worse at last (due to forgetting useful information). While recent studies focused on the deep double descent with respect to model overparameterization, they failed to recognize that sparsity may also cause double descent. In this paper, we have three main contributions. First, we report the novel sparse double descent phenomenon through extensive experiments. Second, for this phenomenon, we propose a novel learning distance interpretation that the curve of 2learning distance of sparse models (from initialized parameters to final parameters) may correlate with the sparse double descent curve well and reflect generalization better than minima flatness. Third, in the context of sparse double descent, a winning ticket in the lottery ticket hypothesis surprisingly may not always win. Copyright © 2022, The Authors. All rights reserved.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Generative cooperative net for image generation and data augmentation 7th

Generative cooperative net for image generation and data aug...

引用

7th International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making, IUKM 2019

作者： Xu, Qiangeng Qin, Zengchang Wan, Tao Intelligent Computing and Machine Learning Lab School of ASEE Beihang University Beijing China Department of Computer Science University of Southern California Los Angeles United States Keep Labs Keep Inc. Beijing China School of Biological Science and Medical Engineering Beihang University Beijing China

ISBN: (纸本)9783030148140

How to build a good model for image generation given an abstract concept is one of fundamental problems in computer vision. In this paper, we explore a generative model for the task of generating fictitious images with desired features. We propose the Generative Cooperative Net (GCN) for image generation. The idea is similar to generative adversarial networks (GANs) except that the generators and discriminators are trained to work accordingly. We conducted experiments on hand-written digit generation and facial expression generation. In experimental studies, we found that GCN’s two cooperative counterparts (the generator and the classifier) can work together nicely and achieve promising results. Such generative model can be used as a data-augmentation tool. Our experiment of applying this method to an emotion classification task shows that the synthesis images can help to improve classification accuracy. It is easy to set up and generate a very large synthesized dataset. © Springer Nature Switzerland AG 2019.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Parallel implementation of apriori algorithm based on MapReduce

Parallel implementation of apriori algorithm based on MapRed...

引用

13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed computing, SNPD 2012

作者： Li, Ning Zeng, Li He, Qing Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Graduate University Chinese Academy of Sciences Beijing 100139 China Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 Hebei China

ISBN: (纸本)9780769547619

Searching frequent patterns in transactional databases is considered as one of the most important data mining problems and Apriori is one of the typical algorithms for this task. Developing fast and efficient algorithms that can handle large volumes of data becomes a challenging task due to the large databases. In this paper, we implement a parallel Apriori algorithm based on MapReduce, which is a framework for processing huge datasets on certain kinds of distributable problems using a large number of computers (nodes). The experimental results demonstrate that the proposed algorithm can scale well and efficiently process large datasets on commodity hardware. © 2012 IEEE.

关键词： MapReduce

来源：评论

学校读者我要写书评

暂无评论

A k-hyperplane-based neural network for non-linear regression

A k-hyperplane-based neural network for non-linear regressio...

引用

IEEE International Conference on Cognitive Informatics

作者： Hongmei He Zengchang Qin Department of Engineering Mathematics University of Bristol Bristol UK Intelligent Computing and Machine Learning Lab School of Automation and Electrical Engineering Beihang University Beijing China

For the time series prediction problem, the relationship between the abstracted independent variables and the response variable is usually strong non-linear. We propose a neural network fusion model based on k-hyperplanes for non-linear regression. A k-hyperplane clustering algorithm is developed to split the data to several clusters. The experiments are done on an artificial time series, and the convergence of k-hyperplane clustering algorithm and neural network gradient training algorithm is examined. The dimension of inputs affect the clustering performance very much. Neural network fusion can get some compensation in performance. It is shown that the prediction performance of the model for the time series is very good. The model can be further exploited for many real applications.

关键词： Artificial neural networks Clustering algorithms Convergence Linear regression Mathematical model Training Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

TuneRank Model for Main Melody Extraction from Multi-part Musical Scores

TuneRank Model for Main Melody Extraction from Multi-part Mu...

引用

International Conference on intelligent Human-machine Systems and Cybernetics, IHMSC

作者： Hanqing Zhao Zengchang Qin École d'Ingénieur Généraliste Beihang University Beijing China Intelligent Computing and Machine Learning Lab. Beihang University China

ISBN: (纸本)9781479949540

A musical part is a strand of music played by an individual instrument within a larger music work, main melody is a single musical part which consists of the most significant melodic elements of multi-part musical score. This part is typically related to dissonance between musical parts and musical instruments. In this paper, we propose a novel model for extracting the main melody from multi-part musical scores. This model is referred to as the TuneRank model that has the conceptually similar idea of the PageRank model. If each musical note can be considered like a web page in the Internet, and the dissonance value between two notes is like the quantity of links between two web pages. The TuneRank (rank of becoming main melody) of each note is calculated using Markov transition probability. This model is tested on the ECPK4 database. By comparing to the previous work, we find that this note-based model is more effective for processing scores containing main melody in multiple parts. Also, the accuracy does not change with the increase of the number of parts. In general, this model can be used for extracting the single-part main melody of digital musical scores.

关键词： Tuners Accuracy Feature extraction Probability Educational institutions Internet

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：