Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

关于参考文献的问题 #90

Closed
pkuwwt opened this issue Jun 3, 2017 · 17 comments
Closed

关于参考文献的问题 #90

pkuwwt opened this issue Jun 3, 2017 · 17 comments

Comments

@pkuwwt
Copy link

pkuwwt commented Jun 3, 2017

出于个人学习的需要,我自己把图片和参考文献给加上了。在校对过程中,发现至少有20多处参考文献和原著没有对应上,即本来是两篇参考文献,但译著中却显示为相同。不知道书籍出版了没有,这些问题有可能对认真阅读的读者带来困扰。

我将原著与译著之间的参考文献对应上,然后发现了如下出问题的映射。这些都是译著一个文献对应原著多个文献的情况。

ElHihi+Bengio-nips8 -> Hihi and Bengio 1996;Hihi and Bengio 1996;El Hihi and Bengio 1996;Hihi and Bengio 1996
Glorot+al-AI-2011-small -> Glorot et al. 2011a;Glorot et al. 2011a;Glorot et al. 2011a;Glorot et al. 2011a;Glorot et al. 2011a;Glorot and Bengio 2010
Goodfellow-et-al-NIPS2014-small -> Goodfellow et al. 2014c;Goodfellow et al. 2014c;Kingma and Welling 2014a;Goodfellow et al. 2014c;Goodfellow et al. 2014c
WardeFarley+al-ICLR2014 -> WardeFarley et al. 2014;Warde-Farley et al. 2014;WardeFarley et al. 2014
Szegedy-et-al-arxiv2014 -> Szegedy et al. 2014a;Szegedy et al. 2014a;Szegedy et al. 2014a;Szegedy et al. 2014a;Szegedy et al. 2014a;Szegedy et al. 2014b;Szegedy et al. 2014a;Szegedy et al. 2014a
Larochelle2008 -> Larochelle and Bengio 2008;Larochelle et al. 2008
Kingma+Welling-ICLR2014 -> Kingma 2013;Kingma and Welling 2014a;Goodfellow et al. 2014c
Graves-et-al-arxiv2014 -> Graves et al. 2014a;Graves et al. 2014b;Graves et al. 2014b
Bengio+Monperrus-2005 -> Bengio and Monperrus 2005;Bengio et al. 2006c;Bengio and Monperrus 2005
Rumelhart86 -> Rumelhart et al. 1986c;Rumelhart et al. 1986b
Hinton-et-al-arxiv2012 -> Hinton et al. 2012a;Hinton et al. 2012c;Hinton et al. 2012c;Hinton et al. 2012c
Hinton-et-al-2012 -> Hinton et al. 2012b;Hinton et al. 2012a
bengio2013estimating -> Bengio 2013;Bengio et al. 2013b;Bengio et al. 2013b
Russakovsky2014imagenet -> Russakovsky et al. 2014a;Russakovsky et al. 2014b
Mnih2013 -> Mnih et al. 2013;Mnih and Kavukcuoglu 2013;Mnih and Kavukcuoglu 2013
Graves-et-al-ICASSP2013 -> Graves et al. 2013;Graves et al. 2013;Graves et al. 2013;Graves et al. 2013;Graves 2013;Graves et al. 2013;Graves et al. 2013;Graves 2013;Graves 2013;Graves et al. 2013;Graves et al. 2013
Bengio91z -> Bengio et al. 1991;Bengio 1991;Bengio et al. 1991
Rumelhart86c -> Rumelhart et al. 1986b;Rumelhart et al. 1986a;Rumelhart et al. 1986b
Hinton06 -> Hinton et al. 2006;Hinton et al. 2006;Hinton et al. 2006;Hinton 2006;Hinton et al. 2006;Hinton et al. 2006;Hinton et al. 2006
Montufar-et-al-NIPS2014 -> Montufar et al. 2014;Montufar et al. 2014;Montufar et al. 2014;Montufar et al. 2014;Montufar et al. 2014;Montúfar 2014
Graves+Schmidhuber-2009 -> Graves and Schmidhuber 2009;Graves et al. 2009

@SwordYork
Copy link
Contributor

@pkuwwt 收到,请问有没有详细的位置?
@exacity/translation 我们核对一下。

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

我回头再整理一下

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

10.9.1
Bengio91z在其它地方对应于Bengio et. al 1991,但此处原文是Bengio 1991

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

据推断,Graves-et-al-ICASSP2013对应于Graves et al. 2013,Graves-arxiv2013对应于Graves 2013

10.5
实验证据\citep{Graves-arxiv2013,
原文是Graves et al. 2013

\cite{Graves-arxiv2013}第一个展示
原文是Graves et al. 2013

10.10.1
手写识别\citep{Graves-et-al-ICASSP2013} 处原文是Graves, 2013,因此很可能是Graves-arxiv2013。

而且原文Handwritting generation应该翻译成手写生成吧?

10章结尾处的Graves-et-al-ICASSP2013也对应于原文的Graves, 2013

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

10章另一处10.11.2
还有学者提出\citep{Graves-et-al-ICASSP2013} 处原文是Graves, 2013

还有一个无约束手写识别\citep{Graves+Schmidhuber-2009},原文是Graves et al. 2009

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

第5章5.1.3
\cite{Mnih2013}介绍了...
原文是Mnih et al, 2013

这个参考文献你们估计漏掉了

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

12章12.1.5
Bengio2013estimating和bengio-arxiv13-condcomp都是指Estimating or propagating gradients through stochastic neurons for conditional computations吧

这里的Bengio2013estimating原文是Bengio, 2013,即文献Deep learning of representation

多个\gls{latent_variable}的形式。
这里缺了一个文献Mnih-Hinton2007

传统的回退~\gls{n_gram}~模型
这里缺了3个文献Jelinek+Mercer80,Katz87,Chen+Goodman99

13章
来学习特征组。
缺了2个文献Hyvarinen-Hoyer1999,Hyvarien2001b

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

第1章1.2.4
Hinton-et-al-arxiv2012}使得语音识别

原文是2012a,这里肯定搞错了,因为译文中多处Hinton-et-al-arxiv2012指向了2012c

我猜应该是Hinton-et-al-2012,另一个地方用的是这个映射

而第5章中
谷歌\citep{Hinton-et-al2012}原文是2012b,因为原文中2012a与2012b是同一篇,因此译文没错。

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

第5章5.11.2
非局部的泛化\citep{},两个文献写成一样了,第二个应该是Bengio2006c

表明,在所有可能的数据生成
这里缺了Wopert1996

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

19章结尾

Kingma-arxiv2013写成了Kingma+Welling-ICLR2014

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

7章7.6
更好的权衡\citep{} 第二个文献应该是Larochelle+Bengio-2008或Larochelle+Bengio-2008-small

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

7章7.14
\gls{adversarial_training}\citep{Szegedy-et-al-arxiv2014

应该是Szegedy-ICLR2014

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

8章8.4
\cite{Glorot+al-AI-2011-small}建议使用

原文是Glorot and Bengio 2010,这个文献大概也漏掉了

@pkuwwt
Copy link
Author

pkuwwt commented Jun 3, 2017

10章
读者可以参考\cite{Schmidhuber96
这里应该是92年那篇

研究者\cite{Jaeger-NIPS2022,...
这里应有4个文献,译文只有3个,缺了Jaeger-2007

14章
的变体\citep{Bengio+Monperrus-2005}
这里原文是Bengio et al. 2006c

15章
是概率分布的\gls{universal_approximator}~\citep
这里5个文献,只给了4个,缺了Leroux-Bengio-2010

暂时确认了的就是这么多了,基本消除一对多的情况。另有三篇原文参考文献是重复的,就无所谓了。

@SwordYork
Copy link
Contributor

@pkuwwt 非常感谢,不一定来得及改。我们尽快确认。

SwordYork added a commit that referenced this issue Jun 11, 2017
@SwordYork
Copy link
Contributor

我自己也检查了一遍,发现你的PDF可能有点滞后,有些问题已经修复。不过大部分你提的问题都是存在的,非常感谢!但纸质版不一定能赶上。

@snowjade
Copy link

snowjade commented Aug 5, 2020

@pkuwwt 偷偷问一下,你加的图片来源是哪里啊? 难道是从有图片的PDF里截图么?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants