卷积神经网络 | 入门文摘

快来打我* 2022-02-03 08:53 246阅读 0赞

（未完待续中）

开篇是摘自网络上的一段话，希望通过本博客，入门卷积神经网络之后，你能较好的理解这段话：

*  **LeNet**. The first successful applications of Convolutional Networks were developed by Yann LeCun in 1990’s. Of these, the best known is the [LeNet][] architecture that was used to read zip codes, digits, etc.
 *  **AlexNet**. The first work that popularized Convolutional Networks in Computer Vision was the [AlexNet][], developed by Alex Krizhevsky, Ilya Sutskever and Geoff Hinton. The AlexNet was submitted to the [ImageNet ILSVRC challenge][] in 2012 and significantly outperformed the second runner-up (top 5 error of 16% compared to runner-up with 26% error). The Network had a similar architecture basic as LeNet, but was deeper, bigger, and featured Convolutional Layers stacked on top of each other (previously it was common to only have a single CONV layer immediately followed by a POOL layer).
 *  **ZF Net**. The ILSVRC 2013 winner was a Convolutional Network from Matthew Zeiler and Rob Fergus. It became known as the[ZFNet][] (short for Zeiler & Fergus Net). It was an improvement on AlexNet by tweaking the architecture hyperparameters, in particular by expanding the size of the middle convolutional layers.
 *  **GoogLeNet**. The ILSVRC 2014 winner was a Convolutional Network from [Szegedy et al.][] from Google. Its main contribution was the development of an Inception Module that dramatically reduced the number of parameters in the network (4M, compared to AlexNet with 60M). Additionally, this paper uses Average Pooling instead of Fully Connected layers at the top of the ConvNet, eliminating a large amount of parameters that do not seem to matter much.
 *  **VGGNet**. The runner-up in ILSVRC 2014 was the network from Karen Simonyan and Andrew Zisserman that became known as the[VGGNet][]. Its main contribution was in showing that the depth of the network is a critical component for good performance. Their final best network contains 16 CONV/FC layers and, appealingly, features an extremely homogeneous architecture that only performs 3x3 convolutions and 2x2 pooling from the beginning to the end. It was later found that despite its slightly weaker classification performance, the VGG ConvNet features outperform those of GoogLeNet in multiple transfer learning tasks. Hence, the VGG network is currently the most preferred choice in the community when extracting CNN features from images. In particular, their [pretrained model][VGGNet] is available for plug and play use in Caffe. A downside of the VGGNet is that it is more expensive to evaluate and uses a lot more memory and parameters (140M).
 *  **ResNet**. [Residual Network][] developed by Kaiming He et al. was the winner of ILSVRC 2015. It features an interesting architecture with special skip connections and features heavy use of batch normalization. The architecture is also missing fully connected layers at the end of the network. The reader is also referred to Kaiming’s presentation ([video][], [slides][]), and some [recent experiments][] that reproduce these networks in Torch.

--------------------

【CNN】Youtube上迄今为止最好的卷积神经网络入门教程（视频）：

[https://www.bilibili.com/video/av16175135][https_www.bilibili.com_video_av16175135]

CNN的两种padding方式“SAME”和“VALID”：

[https://blog.csdn.net/wuzqchom/article/details/74785643][https_blog.csdn.net_wuzqchom_article_details_74785643]

神经网络中的激活函数具体是什么？为什么ReLu要好过于tanh和sigmoid function? ：

[https://www.sohu.com/a/214965417\_100008678][https_www.sohu.com_a_214965417_100008678]

据说：一般来说，全连接层常用的激励函数有tanh和softmax，全连接层之间的连接一般用tanh，全连接层与输出层（预测层）的链接用softmax。（待各位大佬解释）

激活函数简介：

[https://blog.csdn.net/wangqianqianya/article/details/82961276][https_blog.csdn.net_wangqianqianya_article_details_82961276] 当然还有几个，你可以上网自己搜。

**关于激活函数，如果你英文可以，还有更好的一篇英文介绍：**

[https://blog.goodaudience.com/artificial-neural-networks-explained-436fcf36e75?spm=a2c4e.11153940.blogcont637953.10.1f8c45b8QmSlZh][https_blog.goodaudience.com_artificial-neural-networks-explained-436fcf36e75_spm_a2c4e.11153940.blogcont637953.10.1f8c45b8QmSlZh]

**如果你只想看一篇文章入门的话，就是这篇了：**

【一文入门卷积神经网络：CNN通俗解析】[https://yq.aliyun.com/articles/637953][https_yq.aliyun.com_articles_637953]

[LeNet]: http://yann.lecun.com/exdb/publis/pdf/lecun-98.pdf
[AlexNet]: http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks
[ImageNet ILSVRC challenge]: http://www.image-net.org/challenges/LSVRC/2014/
[ZFNet]: http://arxiv.org/abs/1311.2901
[Szegedy et al.]: http://arxiv.org/abs/1409.4842
[VGGNet]: http://www.robots.ox.ac.uk/~vgg/research/very_deep/
[Residual Network]: http://arxiv.org/abs/1512.03385
[video]: https://www.youtube.com/watch?v=1PGLj-uKT1w
[slides]: http://research.microsoft.com/en-us/um/people/kahe/ilsvrc15/ilsvrc2015_deep_residual_learning_kaiminghe.pdf
[recent experiments]: https://github.com/gcr/torch-residual-networks
[https_www.bilibili.com_video_av16175135]: https://www.bilibili.com/video/av16175135
[https_blog.csdn.net_wuzqchom_article_details_74785643]: https://blog.csdn.net/wuzqchom/article/details/74785643
[https_www.sohu.com_a_214965417_100008678]: https://www.sohu.com/a/214965417_100008678
[https_blog.csdn.net_wangqianqianya_article_details_82961276]: https://blog.csdn.net/wangqianqianya/article/details/82961276
[https_blog.goodaudience.com_artificial-neural-networks-explained-436fcf36e75_spm_a2c4e.11153940.blogcont637953.10.1f8c45b8QmSlZh]: https://blog.goodaudience.com/artificial-neural-networks-explained-436fcf36e75?spm=a2c4e.11153940.blogcont637953.10.1f8c45b8QmSlZh
[https_yq.aliyun.com_articles_637953]: https://yq.aliyun.com/articles/637953