检索结果-内蒙古大学图书馆

A SURVEY OF AUTOMATIC GENERATION OF SOURCE CODE COMMENTS: ALGORITHMS AND TECHNIQUES

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Song, Xiaotao Sun, Hailong Wang, Xu Yan, Jiafei School of Software Taiyuan University of Technology China SKLSDE Lab School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

As an integral part of source code files, code comments help improve program readability and comprehension. However, developers sometimes do not comment on their program code adequately due to the incurred extra efforts, lack of relevant knowledge, unawareness of the importance of code commenting or some other factors. As a result, code comments can be inadequate, absent or even mismatched with source code, which affects the understanding, reusing and the maintenance of software. To solve these problems of code comments, researchers have been concerned with generating code comments automatically. In this work, we aim at conducting a survey of automatic code commenting researches. First, we generally analyze the challenges and research framework of automatic generation of program comments. Second, we present the classification of representative algorithms, the design principles, strengths and weaknesses of each category of algorithms. Meanwhile, we also provide an overview of the quality assessment of the generated comments. Finally, we summarize some future directions for advancing the techniques of automatic generation of code comments and the quality assessment of comments. Copyright © 2019, The Authors. All rights reserved.

关键词： Surveys

Rely-Guarantee Reasoning about Messaging System for Autonomous Vehicles

学校读者我要写书评

暂无评论

Rely-Guarantee Reasoning about Messaging System for Autonomo...

Theoretical Aspects of Software Engineering (TASE)

作者： Wenjing Xu Yongwang Zhao Dianfu Ma YuXin Zhang Qian Xiao State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang Univerisity Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China State Key Laboratory of Automotive Simulation and Control College of Automotive Engineering Jilin University Jilin China School of Computer Science and Technology Guizhou University Guiyang China

Messaging system as a communicating infrastructure is a safety-critical component of autonomous vehicles. For the purpose of safety certification of Level 4 autonomous driving systems, its necessary to provide a formally verified specification of messaging systems. This paper presents a realistic case study using the PiCore rely-guarantee framework to formally verify the DGPS (Differential Global Positioning System) of UISEE autonomous driving systems. We first create an axiom model of messaging systems by extending PiCore, which is reusable for concrete applications. The model supports dynamic configuration of message buffers as well as the automatic generation of the rely and guarantee conditions for compositional reasoning. It is instantiated when developing the formal specification of DGPS. Then, we use the rely-guarantee proof system of PiCore to verify the functional correctness and invariant of DGPS. The specification and its proof provide a strong evidence for the ongoing safety certification of DGPS.

关键词： Cognition Safety Formal specifications Vehicle dynamics Autonomous vehicles Certification Global Positioning System

Efficient Block Pruning Based on Kernel and Feature Stablization

学校读者我要写书评

暂无评论

Efficient Block Pruning Based on Kernel and Feature Stabliza...

Proceedings of the Digital Image computing: Technqiues and Applications (DICTA)

作者： Sheng Xu Hanlin Chen Kexin Liu Jinhu Lii Baochang Zhang School of Automatic Science and Electrical Engineering Beihang University China State Key Laboratory of Software Development Environment Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China

With the development of computer vision research, the architecture of convolutional neural network becomes more and more complex to reach the state-of-the-art performance. Is the complexity of the model necessarily proportional to its accuracy? To answer this, the compression of the network has attracted much attention in the academy and industry. Existing network pruning methods mostly rely on the scoring mechanism of complexity or diversity of kernels to compress the network, and then build the network model after removing the kernels by tuning or training on the input data. These methods are cumbersome and depend on a well-trained pre-trained model. In this paper, we propose an end-to-end block pruning method based on kernel and feature stability by pruning blocks efficiently. To accomplish this, we firstly introduce a mask to scale the output of the blocks, and the L1 regularization term to monitor the mask update. Second, we introduce the Center Loss to guarantee that the feature does not deviate greatly during learning. To converge fast, we introduce fast iterative shrinkage-thresholding algorithm (FISTA) to optimize the mask, by which a more fast and reliable pruning process is achieved. We implement experiments on different datasets, including CIFAR-10 and ImageNet ILSVRC2012. All the experiments have achieved the state-of-the-art accuracy.

关键词：

Poster: Semantically enhanced tag recommendation for software CQAs via deep learning 40

学校读者我要写书评

暂无评论

Poster: Semantically enhanced tag recommendation for softwar...

40th ACM/IEEE International Conference on Software Engineering, ICSE 2018

作者： Zhang, Jian Sun, Hailong Tian, Yanfei Liu, Xudong SKLSDE Lab School of Computer Science and Engineering Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100191 China

ISBN: (纸本)9781450356633

Most software CQAs (e.g. Stack Overflow) mainly rely on users to assign tags for posted questions. This leads to many redundant, inconsistent and inaccurate tags that are detrimental to the communities. Therefore tag quality becomes a critical challenge to deal with. In this work, we propose STR, a deep learning based approach that automatically recommends tags through learning the semantics of both tags and questions in such software CQAs. First, word embedding is employed to convert text information to high-dimension vectors for better representing questions and tags. Second, a Multi-Tasking-like Convolutional Neural Network, the core modules of STR, is designed to capture short and long semantics. Third, the learned semantic vectors are fed into a gradient descent based algorithm for classification. Finally, we evaluate STR on three datasets collected from popular software CQAs, and experimental results show that STR outperforms state-of-The-Art approaches in terms of Precision@k, Recall@k and F1-Measure@k. © 2018 Authors.

关键词： Semantics

Magnetic skyrmions for unconventional computing

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Sai Kang, Wang Zhang, Xichao Nie, Tianxiao Zhou, Yan Wang, Kang L. Zhao, Weisheng School of Integrated Circuit Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China Shenyuan Honors College Beihang University Beijing100191 China School of Science and Engineering Chinese University of Hong Kong Shenzhen518172 Hong Kong Department of Electrical and Computer Engineering University of California Los AngelesCA90095 United States

Improvements in computing performance have significantly slowed down over the past few years owing to the intrinsic limitations of computing hardware. However, the demand for data computing has increased exponentially. To solve this problem, tremendous attention has been focused on the continuous scaling of the Moore’s Law as well as the advanced non-von Neumann computing architecture. A rich variety of unconventional computing paradigms has been raised with the rapid development of nanoscale devices. Magnetic skyrmions, spin swirling quasiparticles, have been endowed with great expectations for unconventional computing due to their potential as the smallest information carriers by exploiting their physics and dynamics. In this paper, we provide an overview of the recent progress of skyrmion-based unconventional computing from a joint device-application perspective. This paper aims to build up a panoramic picture, analyze the remaining challenges, and most importantly to shed light on the outlook of skyrmion based unconventional computing for interdisciplinary researchers. Copyright © 2020, The Authors. All rights reserved.

关键词： Magnetism

Leveraging Graph Neural Network with LSTM For Traffic Speed Prediction

学校读者我要写书评

暂无评论

Leveraging Graph Neural Network with LSTM For Traffic Speed ...

Symposia and Workshops on Ubiquitous, Autonomic and Trusted computing, UIC-ATC

作者： Zhilong Lu Weifeng Lv Zhipu Xie Bowen Du Runhe Huang State Key Lab of Software Development Environment Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Hosei University Tokyo Japan

ISBN: (数字)9781728140346

ISBN: (纸本)9781728140353

Accurate traffic forecasting plays an important role in the smart city and is of great significance for urban traffic planning, management, and traffic control. However, road speed prediction is a challenge task due to the complex topological structure of road networks and stochastic traffic patterns. For capturing spatial and temporal dependencies simultaneously, in this paper we propose a novel graph neural network based traffic speed forecasting model, the graph Long short term Memory (GLSTM) model which consists Graph neural network (GNN) and Long short term Memory. To the best of our knowledge, this is the first time to combine LSTM and GNN to feed graph-structured data as input for train models in traffic speed prediction. More specifically, at first we construct a unweighted directed graph from road network and feed LSTM cell with graph-structured data. After that, we train the whole model based on encoder-decoder architecture and message-passing mechanism of GNN. Experiments show that our proposed method is able to utilize road structure to capture spatial-temporal dependencies based on GNN while capture long-term dependencies based on LSTM. The result of real world dataset shows that proposed method outperform state-of-the-art baseline methods.

关键词： Roads Forecasting Predictive models Recurrent neural networks Machine learning Accidents

Adaptive NMS: Refining pedestrian detection in a crowd

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Songtao Huang, Di Wang, Yunhong Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Software Development Environment Beihang University School of Computer Science and Engineering Beihang University Beijing100191

Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel NonMaximum Suppression (NMS) algorithm to better refine the bounding boxes given by detectors. The contributions are threefold: (1) we propose adaptive-NMS, which applies a dynamic suppression threshold to an instance, according to the target density;(2) we design an efficient subnetwork to learn density scores, which can be conveniently embedded into both the single-stage and two-stage detectors;and (3) we achieve state of the art results on the CityPersons and CrowdHuman benchmarks. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

Adaptive unimodal cost volume filtering for deep stereo matching

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Youmin Chen, Yimin Bai, Xiao Yu, Suihanjin Yu, Kun Li, Zhiwei Yang, Kuiyuan State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Jiangxi Research Institute Beihang University Beijing China DeepMotion

State-of-the-art deep learning based stereo matching approaches treat disparity estimation as a regression problem, where loss function is directly defined on true disparities and their estimated ones. However, disparity is just a byproduct of a matching process modeled by cost volume, while indirectly learning cost volume driven by disparity regression is prone to overfitting since the cost volume is under constrained. In this paper, we propose to directly add constraints to the cost volume by filtering cost volume with unimodal distribution peaked at true disparities. In addition, variances of the unimodal distributions for each pixel are estimated to explicitly model matching uncertainty under different contexts. The proposed architecture achieves state-of-the-art performance on Scene Flow and two KITTI stereo benchmarks. In particular, our method ranked the 1st place of KITTI 2012 evaluation and the 4th place of KITTI 2015 evaluation (recorded on 2019.8.20). The codes of AcfNet are available at: https://***/DeepMotionAIResearch/ DenseMatchingBenchmark. Copyright © 2019, The Authors. All rights reserved.

关键词： Uncertainty analysis

Improving Spectral Clustering with Deep Embedding and Cluster Estimation

学校读者我要写书评

暂无评论

Improving Spectral Clustering with Deep Embedding and Cluste...

IEEE International Conference on data Mining (ICDM)

作者： Liang Duan Charu Aggarwal Shuai Ma Saket Sathe SKLSDE Lab Beihang University China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing China IBM T. J. Watson Research Center New York USA

Spectral clustering is one of the most popular modern clustering algorithms. It is easy to implement, can be solved efficiently, and very often outperforms other traditional clustering algorithms such as k-means. However, pectral clustering would be insufficient when dealing with most datasets which have complex statistical properties and quires the user to specify the number of clusters (called k). To address these two problems, in this paper, we propose an approach to extending spectral clustering with deep embedding and estimation of the number of clusters. Specifically, we first generate the deep embedding via learning a deep autoencoder, which transforms the raw data into the lower dimensional representations that suitable for clustering. We then provide an effective method to estimate the number of clusters by learning a softmax autoencoder from the deep embedding. We finally extend spectral clustering with the learned embedding and the estimated number. An extensive experimental study on several image and text datasets illustrates the effectiveness and efficiency of our approach.

关键词：