【摘 要】
:
Deep learning has developed rapidly in recent years,attracting the attention of numerous re-searchers.Since a wide range of topics are covered in this field,we are wondering what topics researchers have concerned about.However,after investigation,we find
【机 构】
:
State Key Laboratory for Novel Software Technology,Nanjing University,Nanjing 210093,China;School of
论文部分内容阅读
Deep learning has developed rapidly in recent years,attracting the attention of numerous re-searchers.Since a wide range of topics are covered in this field,we are wondering what topics researchers have concerned about.However,after investigation,we find that very few researchers have paid attention to this demand.In this paper,we conduct a large-scale study to analyze the questions faced by deep learning developers.We use Stack Overflow,one of the largest question&answer sites,as our data source,and extract 32969 posts about deep learning as our studied dataset.After filtering,augmenting and pre-processing the post datasets from Stack Overflow,we use the latent Dirichlet allocation (LDA) topic model to summarize 30 topics based on their text content.In addition,we measure the difficulty and popularity of each topic,compare the different issues faced by different deep learning frameworks,and analyze the development trend of each topic.Our main results are as follows:(1) developers ask a broad spectrum of questions about deep-learning,ranging from Data Shape to Object Detection;(2) Gradient Propagation is the most popular among all the topics and (3) Object Detection is the most difficult;(4) issues of Package Installation,Code Understanding and Method Introduction are common in the current different deep learning frameworks;(5) there are three trends in these topics,e.g.,a significant rising trend is found in the number of discussion on Data Shape.Finally,based on our research findings,we make some targeted and valuable suggestions for developers,researchers,educators,and framework providers of deep learning.
其他文献
东非造山带作为全球出露较完整的前寒武系造山带之一,蕴藏了丰富的矿产资源.在查阅苏丹、厄立特里亚、埃塞俄比亚基础地质资料的基础上,将研究区划分为撒哈拉、东非和东冈瓦纳3个地层大区,进一步划分出Nukheila、Zalingei、Bayuda、Muglad-Kosti、努比亚、莫桑比克、East Ogaden和West Ogaden 8个地层区.其中,努比亚地层区和莫桑比克地层区划分出Cabgaba地体、Gebeit地体、Haya地体、Barka地体、Hagar地体、Adobha Abiy地体、Nacfa地体
几内亚大地构造位置处于西非克拉通南部,主要受Libérien、Eburnéen及泛非三次大的造山运动影响,主要的地质单元包括东部太古宙—古元古代马莱地盾、西部古生代博法(Bove)盆地和西南部泛非期Rokelide造山带.在广泛调研文献的基础上,着重介绍了几内亚铝土矿、铁、金等矿产资源的开发现状.结合区域地质背景和典型矿床分析,剖析了这3种优势金属矿产的成矿作用,认为几内亚超大规模的铝土矿资源是地质历史时期区域构造、成矿母岩、气候、地形地貌、水文地质等多种因素耦合作用的结果.几内亚拥有世界上规模最大的未开
尼日利亚是非洲人口和经济第一大国,是中国“一带一路”倡议与中非合作的重要组成部分.该国矿产资源丰富,锂矿、锡铌钽矿、金矿和铁矿成矿条件好,找矿潜力大,但是其地质工作程度较低,大部分矿产尚未进行勘探,具有良好的投资前景.乔斯-包奇花岗岩型稀有金属成矿带和中西部金及伟晶岩型稀有金属成矿带的金矿、锂矿和铌钽矿为目前中资企业投资的热点地区和矿种.在矿业政策方面,尼日利亚将矿业激励措施制度化,进一步提高其矿业对外国投资者的吸引力.通过尼日利亚矿产资源的开发现状和矿业投资环境的分析,提出了尼日利亚矿业投资建议,对中资
莫桑比克位于非洲东南部,是加强“一带一路”矿业产能合作的重要国家.在研究莫桑比克矿产资源分布特征、重要矿山开发现状的基础上,从政局稳定性、营商环境等方面对中资企业赴莫开展矿业投资的前景进行了分析.结合优势矿种分布、重要矿山开发现状、投资环境等因素,莫桑比克的优势资源油气主要分布于森托奥-鲁伍玛-赞比西-马普托成矿带的鲁伍玛盆地和莫桑比克盆地,煤主要位于森托奥-赞比西成矿带,钛、锆集中于森托奥-鲁伍玛-赞比西-马普托成矿带滨海地区,金主要分布于尼亚萨-安格尼亚-津巴布韦成矿带及津巴布韦-森托奥-巴鲁埃成矿带
在实施“走出去”战略和推进“一带一路”倡议的背景下,近年中资企业在国际矿业投资领域得到了快速发展.刚果(金)铜、钴、金刚石、锡、钽铌等矿产的资源量在全球占有重要地位,加之近年政府吸引和鼓励外来投资的利好政策,使之成为全球最火的矿业投资热土之一.从区域地质、矿产资源及开发现状、基础设施、矿业投资环境等方面对刚果(金)的地质矿产概况进行了梳理.钴和铜是刚果(金)最丰富的2种金属矿产,集中分布在南部加丹加地区.铜钴矿业开发活跃,是刚果(金)重要的经济支柱.加丹加地区是刚果(金)经济发展和基础设施最好的地区之一,
Representation learning on textual network or textual network embedding,which leverages rich textual information associated with the network structure to learn low-dimensional embedding of vertices,has been useful in a variety of tasks.However,most approa
Computing the weighted girth,which is the sum of weights of edges in the minimum weight cycle,is an important problem in network analysis.The problem for distributively computing girth in unweighted graphs has garnered lots of attention,but there are few
Convolutional neural networks (CNNs) obtain promising results via layered kernel convolution and pooling operations,yet the learning dynamics of the kernel remain obscure.We propose a continuous form to describe kernel-based convolutions through integrati
Several modern network embedding methods learn vector representations from sampled context nodes.The sampling strategies are often carefully designed and controlled by specific parameters that enable them to adapt to different networks.However,the followi
This paper deals with the problem of fixed-time attitude tracking control for spacecraft subject to model uncertainties and external disturbances.Firstly,by using a fixed-time extended state observer(FxTESO),the synthetic uncertainties generated by extern