LaTeX IEEE模板

marsggbo

发布于 2018-11-09 16:13:39

1.6K0

发布于 2018-11-09 16:13:39

文章被收录于专栏：AutoML(自动机器学习)AutoML(自动机器学习)AutoML(自动机器学习)

因为课程作业的要求需要完成一篇IEEE格式的论文，所以选择入门LaTeX。但是期间遇到了各种各样莫名其妙的坑。前前后后挣扎了两个多星期终于完成了IEEE模板的设置。下面详细记录一下让我深恶痛绝的心路历程。

一、软件的选择

网上有很多LaTeX软件，在线编辑器推荐Overleaf。但是我个人还是更喜欢离线写东西，所以尝试过各种编辑器，例如VSCode等等，这些编辑器都需要自己搭环境才能用，反正对于我们这种初学者而言门槛较高，而且浪费时间，所以下面介绍一个LaTeX组合可以让你直接上手体验LaTeX，而不需要挣扎在LaTeX的门口。

要想离线使用LaTeX，首先需要一个编辑器，也就是敲LaTeX的软件，这里强烈推荐 TextStudio。这个软件是开源免费的，而且界面是我找过的软件中还过得去的。。因为感觉其他的也都不怎么好看。

但是光有编辑器还不行啊，你还得有编译器，这里推荐使用 MiKTeX。怎么理解这个软件的作用呢，就好像你要运行python代码，你得安装官网提供的Python3.6或者Anaconda之后才能编译python代码啊，之前没搞懂这个关系，一直以为跟markdown一样，结果并不是。

所以综上，要想使用LaTeX，你得有编辑器和编译器才行啊。

二、模板

废话不多说直接上模板。模板最初只需要如下三个文件：

temp.tex: 保存LaTeX的文件
temp.bib: 保存参考文献的文件，其实也可以将参考文献写在*.tex中，但是我个人更喜欢把他们分开，因为这样逻辑更清晰。
ieeeconf.cls: IEEE样式模板。

以上文件可在如下网址下载：

最终效果：

下面是示例。

1. temp.tex

\documentclass[a4paper, 10pt, conference]{ieeeconf}   
\usepackage[utf8]{inputenc}
\usepackage{dtk-logos} % for BibTeX stylized logo 
\overrideIEEEmargins


\title{\LARGE \bf
The review of Automated Machine learning
}

\author{He Xin$^{1}$ and Wang Zhichun$^{2}$
}

\begin{document}

\maketitle
%\thispagestyle{empty}
%\pagestyle{empty}

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\begin{abstract}

Test test testTest test testTest test testTest test test

Test test testTest test testTest test testTest test test


\end{abstract}

\section{INTRODUCTION}

As we all know(\cite{xie_genetic_2017}), deep learning, which has been used in a lot of research fields including image classification, image recognition, machine translation, has achieved remarkable achievements in those tasks. Take the image classification as an example, AlexNet () outperformed traditional computer vision methods on ImageNet (Russakovsky et al., 2015), which was in turn outperformed by VGG nets (Simonyan \& Zisserman, 2015), then ResNets (He et al., 2016) etc.


\section{METHODS}

As we all know(\cite{xie_genetic_2017}), deep learning, which has been used in a lot of research fields including image classification, image recognition, machine translation, has achieved remarkable achievements in those tasks. Take the image classification as an example, AlexNet () outperformed traditional computer vision methods on ImageNet (Russakovsky et al., 2015), which was in turn outperformed by VGG nets (Simonyan \& Zisserman, 2015), then ResNets (He et al., 2016) etc.


\subsection{Bayesian Optimization}

Test test testTest test testTest test testTest test test
As we all know(\cite{xie_genetic_2017}), deep learning, which has been used in a lot of research fields including image classification, image recognition, machine translation, has achieved remarkable achievements in those tasks. Take the image classification as an example, AlexNet () outperformed traditional computer vision methods on ImageNet (Russakovsky et al., 2015), which was in turn outperformed by VGG nets (Simonyan \& Zisserman, 2015), then ResNets (He et al., 2016) etc.



\subsection{Gradient-based}

Test test testTest test testTest test testTest test test
As we all know(\cite{xie_genetic_2017}), deep learning, which has been used in a lot of research fields including image classification, image recognition, machine translation, has achieved remarkable achievements in those tasks. Take the image classification as an example, AlexNet () outperformed traditional computer vision methods on ImageNet (Russakovsky et al., 2015), which was in turn outperformed by VGG nets (Simonyan \& Zisserman, 2015), then ResNets (He et al., 2016) etc.




\subsection{Meta Learning}

Test test testTest test testTest test testTest test test

As we all know(\cite{xie_genetic_2017}), deep learning, which has been used in a lot of research fields including image classification, image recognition, machine translation, has achieved remarkable achievements in those tasks. Take the image classification as an example, AlexNet () outperformed traditional computer vision methods on ImageNet (Russakovsky et al., 2015), which was in turn outperformed by VGG nets (Simonyan \& Zisserman, 2015), then ResNets (He et al., 2016) etc.





\subsection{Evolutionary Algorithm}
Test test testTest test testTest test testTest test test


As we all know(\cite{xie_genetic_2017}), deep learning, which has been used in a lot of research fields including image classification, image recognition, machine translation, has achieved remarkable achievements in those tasks. Take the image classification as an example, AlexNet () outperformed traditional computer vision methods on ImageNet (Russakovsky et al., 2015), which was in turn outperformed by VGG nets (Simonyan \& Zisserman, 2015), then ResNets (He et al., 2016) etc.




\subsection{Reinforcement Learning}


Test test testTest test testTest test testTest test test

Test test testTest test testTest test testTest test test

Test test testTest test testTest test testTest test test



\section{Comparison and Analysis}

Test test testTest test testTest test testTest test test
Test test testTest test testTest test testTest test test

Test test testTest test testTest test testTest test test

\subsection{Units}


Test test testTest test testTest test testTest test test
Test test testTest test testTest test testTest test test

Test test testTest test testTest test testTest test test


\begin{itemize}

\item Test test test
\item Test test test

\end{itemize}



\section{CONCLUSIONS}


Test test testTest test testTest test testTest test test

Test test testTest test testTest test testTest test test

Test test testTest test testTest test testTest test test

\addtolength{\textheight}{-12cm}   % This command serves to balance the column lengths
                                  % on the last page of the document manually. It shortens
                                  % the textheight of the last page by a suitable amount.
                                  % This command does not take effect until the next page
                                  % so it should come on the page before the last. Make
                                  % sure that you do not shorten the textheight too much.

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%



%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%



%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\section*{APPENDIX}

Test test
Test test testTest test testTest test testTest test test

Test test testTest test testTest test testTest test test

\section*{ACKNOWLEDGMENT}

Test test testTest test testTest test testTest test test

Test test testTest test testTest test testTest test test
Test test

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%


\nocite{*}
\bibliographystyle{ieeetran}
\bibliography{temp}


\end{document}

2. temp.bib

@article{xie_genetic_2017,
    title = {Genetic {CNN}},
    url = {http://arxiv.org/abs/1703.01513},
    abstract = {The deep Convolutional Neural Network (CNN) is the state-of-the-art solution for large-scale visual recognition. Following basic principles such as increasing the depth and constructing highway connections, researchers have manually designed a lot of ﬁxed network structures and veriﬁed their effectiveness.},
    language = {en},
    urldate = {2018-10-22},
    journal = {arXiv:1703.01513 [cs]},
    author = {Xie, Lingxi and Yuille, Alan},
    month = mar,
    year = {2017},
    note = {arXiv: 1703.01513},
    keywords = {Computer Science - Computer Vision and Pattern Recognition},
    file = {Xie 和 Yuille - 2017 - Genetic CNN.pdf:E\:\\Zotero_storage\\storage\\A73TXSBC\\Xie 和 Yuille - 2017 - Genetic CNN.pdf:application/pdf}
}