检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Zhang, Chunxu Cui, Jiaxu Yang, Bo College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China

In recent years, deep learning has achieved remarkable achievements in many fields, including computer vision, natural language processing, speech recognition and others. Adequate training data is the key to ensure the effectiveness of the deep models. However, obtaining valid data requires a lot of time and labor resources. Data augmentation (DA) is an effective alternative, which can generate new labeled data based on existing data using label-preserving transformations. Although we can benefit a lot from DA, designing appropriate DA policies requires a lot of expert experience and time consumption, and the evaluation of searching the optimal policies is costly. So we raise a new question in this paper: how to achieve automated data augmentation at as low cost as possible? We propose a method named BO-Aug for automating the process by finding the optimal DA policies using the Bayesian optimization approach. We validate the BO-Aug on three widely used image classification datasets, including CIFAR-10, CIFAR- 100 and SVHN. Experimental results show that the proposed method can achieve state-of-the-art or near advanced classification accuracy at a relatively low policies search cost, and the searched policies based on a specific dataset are transferable across different neural network architectures or even different datasets. Code to reproduce our experiments is available at https://***/zhangxiaozao/BOAug. Copyright © 2019, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Recruitment-imitation mechanism for evolutionary reinforcement learning

arXiv

引用

arXiv 2019年

作者： Lü, Shuai Han, Shuai Zhou, Wenbo Zhang, Junwei Key Laboratory of Symbolic Computation and Knowledge Engineering Jilin University Ministry of Education Changchun130012 China College of Computer Science and Technology Jilin University Changchun130012 China

Reinforcement learning, evolutionary algorithms and imitation learning are three principal methods to deal with continuous control tasks. Reinforcement learning is sample efficient, yet sensitive to hyper-parameters setting and needs efficient exploration;Evolutionary algorithms are stable, but with low sample efficiency;Imitation learning is both sample efficient and stable, however it requires the guidance of expert data. In this paper, we propose Recruitment-imitation Mechanism (RIM) for evolutionary reinforcement learning, a scalable framework that combines advantages of the three methods mentioned above. The core of this framework is a dual-actors and single critic reinforcement learning agent. This agent can recruit high-fitness actors from the population of evolutionary algorithms, which instructs itself to learn from experience replay buffer. At the same time, low-fitness actors in the evolutionary population can imitate behavior patterns of the reinforcement learning agent and improve their adaptability. Reinforcement and imitation learners in this framework can be replaced with any off-policy actor-critic reinforcement learner or data-driven imitation learner. We evaluate RIM on a series of benchmarks for continuous control tasks in Mujoco. The experimental results show that RIM outperforms prior evolutionary or reinforcement learning methods. The performance of RIM's components is significantly better than components of previous evolutionary reinforcement learning algorithm, and the recruitment using soft update enables reinforcement learning agent to learn faster than that using hard update. Copyright © 2019, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

A Surrogate Model Based Genetic Algorithm for Complex Problem Solving

引用

Journal of Physics: Conference Series 2020年第1期1646卷

作者： Ying Pei Hao Gao Xiaosong Han The College of Information Engineering Changchun University of Finance and Economics Changchun 130122 China Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology College of Software Jilin University Changchun 130012 China

It is well known that when the fitness function is relatively complex, the optimization time cost of the genetic algorithm will be extremely huge. To address this issue, the surrogate model was employed to predict the fitness value of the optimization problem, to reduce the number of actual calculated fitness values. In this paper, BP neural network, the least square method and support vector machine were fused in the genetic algorithm to evaluate partial individuals' fitness. Sufficient benchmark numerical experiments were conducted, and the results proved that the strategy could reduce the calculating counts of fitness function on similar accuracy basis compared with simple genetic algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Correction to: MRI enhancement based on visual-attention by adaptive contrast adjustment and image fusion

引用

Multimedia Tools and Applications 2021年第9期80卷 13019-13019页

作者： Rui Zhu Xiongfei Li Xiaoli Zhang Xiaowei Xu Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China College of Computer Science and Technology Jilin University Changchun China Department of Information Sciences University of Arkansas at Little Rock Little Rock USA

A Correction to this paper has been published: https://***/10.1007/s11042-021-10782-7

关键词：

来源：评论

学校读者我要写书评

暂无评论

Friend Recommendation System Based on Geolocation and Contents of Users

Friend Recommendation System Based on Geolocation and Conten...

引用

2018 International Conference on Computer Modeling, Simulation and Algorithm（CMSA2018）

作者： Mingyue Duan Jing Huang Jiaxuan Zhang Yunjie Tian Dongwei Li Bin Wang College of Computer Science and Technology Jilin university Key Laboratory of Symbol Computation and Knowledge Engineering (Jilin university) Ministry of Education

ISBN: (纸本)9781510864696

In recent years, with the rapid development of wireless mobile network and smart phone operating systems, various social software based on wireless Internet has emerged one after another. Current popular social software such as QQ and We Chat have become important tools for people to meet new friends. At present, existing social software can recommend other users in the vicinity according to the geographical location of the user. However, this method does not consider the user's interests, hobbies, etc. So that the effectiveness of such a friend recommmendation system is often unsatisfactory. In order to solve the above problems, a personalized friend recommendation system based on geolocation information and user content is designed and developed. In this system, not only the geolocation information of the user is considered, but also the features of the user's published statuses are extracted, aiming to recommend more similar other users to the user. After testing, the effectiveness of the proposed method is verified.

关键词： instant message friend recommendation geolocation information context information

来源：评论

学校读者我要写书评

暂无评论

Black-box expectation propagation for Bayesian models

Black-box expectation propagation for Bayesian models

引用

2018 SIAM International Conference on Data Mining, SDM 2018

作者： Li, Ximing Li, Changchun Chi, Jinjin Ouyang, Jihong Wang, Wenting College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University China College of Mathematics Jilin University China

In this paper, we develop a generic black-box expectation propagation (BBEP) algorithm that can be directly applied to Bayesian models without model-specific derivations. BBEP is built on the spirit of using Monte Carlo estimates, where the moment matching step in EP is replaced with Monte Carlo approximations. To avoid high variance, we employ importance sampling for variance reduction and analyze how to find an optimal proposal distribution. We compare BBEP against the state-of-the-art black-box algorithms on both synthetic and real-world data sets. The experimental results indicate that BBEP can reach better predictive performance than baseline algorithms, and even can be on a par with analytical solutions in some settings. © 2018 by SIAM.

关键词： Importance sampling

来源：评论

学校读者我要写书评

暂无评论

A Fuzzy Clustering Based Collaborative Filtering Algorithm for Time-aware POI Recommendation

引用

Journal of Physics: Conference Series 2021年第1期1746卷

作者： Minghao Yin Yanheng Liu Xu Zhou Geng Sun College of Computer Science and Technology Jilin University Changchun Jilin China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun Jilin China Center for Computer Fundamental Education Jilin University Changchun Jilin China

Location based social network develops and gets widely concern along with the population and widespread use of mobile. Point of interest(POI) recommendation become one of the most widely application among location-based service. To get better POI recommendation performance, a fuzzy clustering based collaborative filtering algorithm (FCCF) for time-aware POI recommendation is proposed in this paper. It first constructs the user feature vector from users' check-in behaviours. Individual's check-in behaviour can be under the influence of location region and time slots, so user's feature consists of two parts. One is the vising frequency of each user in different location regions, and the other is the vising frequency of each user in different time slots. Next fuzzy c-means is adopted due to its simplicity to group users according to user feature vector. Then the user similarity computation can be limited in the similar small user groups. In the end, a collaborative filtering algorithm is applied to recommend a number of top-N POIs at a given time for the target user. Some experiments are conducted and the comparative results on Foursquare and Gowalla show that FCCF has higher precision and recall value than the comparative algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A multi-level neural network for implicit causality detection in Web texts

arXiv

引用

arXiv 2019年

作者： Liang, Shining Zuo, Wanli Shi, Zhenkun Wang, Sen Wang, Junhu Zuo, Xianglin Key Laboratory of Symbol Computation Knowledge Engineering of Ministry of Education Changchun China College of Computer Science and Technology Jilin University Jilin China Tianjin Institute of Industrial Biotechnology Chinese Academy of Sciences School of Information Technology and Electrical Engineering The University of Queensland Brisbane Australia School of Information and Communication Technology Griffith University QLD Australia

Mining causality from text is a complex and crucial natural language understanding task corresponding to the human cognition. Existing studies at its solution can be grouped into two primary categories: feature engineering based and neural model based methods. In this paper, we find that the former has incomplete coverage and inherent errors but provide prior knowledge;while the latter leverages context information but causal inference of which is insufficiency. To handle the limitations, we propose a novel causality detection model named MCDN to explicitly model causal reasoning process, and furthermore, to exploit the advantages of both methods. Specifically, we adopt multi-head self-attention to acquire semantic feature at word level and develop the SCRN to infer causality at segment level. To the best of our knowledge, with regards to the causality tasks, this is the first time that the Relation Network is applied. The experimental results show that: i) the proposed approach performs prominent performance on causality detection;ii) further analysis manifests the effectiveness and robustness of MCDN. © 2019, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Design of vehicle automatic braking systems considering drivers' braking characteristics

引用

International Journal of Performability engineering 2019年第9期15卷 2338-2345页

作者： Gao, Zhenhai Sun, Tianjun Hassan, MuHammad Wang, Liupu College of Automotive Engineering Jilin University Changchun130022 China College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbol Computation Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Cancer Hospital Attached Xinjiang Medical University Urumqi830000 China Department of Computer Science and Information Technology University of Malakand KP Pakistan

With the rapid development of advanced driver assistance systems (ADAS), an automatic braking system has become increasingly important when faced with complicated traffic. The conventional decision-making method for the braking system is focused on security but lacks consideration of drivers' characteristics, which generates feelings of fear and frustration. We propose an anthropomorphic braking method based on vehicle kinematic characteristics and dynamic theories to improve the original system and eliminate the sense of jerking. Furthermore, on the basis of the traditional time to collision (TTC) algorithm, we consider the random motion of the target vehicle and develop a dynamic time to collision (DTTC) algorithm to meet different drivers' braking requirements. Therefore, in this study, the braking model is optimized by a series of driving simulator and real-vehicle braking tests. Finally, the validity and feasibility of the method are verified through the simulations of different braking modes. © 2019 Totem Publisher, Inc. All rights reserved.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

A Registration Method for Augmented Reality System Based on Visual SLAM

A Registration Method for Augmented Reality System Based on ...

引用

International Conference on Electronic engineering and Informatics (EEI)

作者： Zuoming Zhang Man Shu Zixuan Wang Hanwen Wang Xin Wang College of Software Engineering Jilin University Changchun China College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University Changchun China

ISBN: (纸本)9781728140773

In augmented reality, smart devices need to sense their own position in real physical space and complex scene structure to achieve good virtual reality interaction and three-dimensional registration. This paper proposes a technical framework of visual SLAM, which uses VO and BA methods based on feature points to obtain pose, and applies it to the augmented reality system to realize pose estimation, registration, tracking, collision and other effects of intelligent equipment independent of artificial or natural landmarks.

关键词： augmented reality image registration pose estimation robot vision SLAM (robots) augmented reality pose estimation robot vision image registration supersonic low altitude missile Registration

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：