Scribd
Upload
36 views15 pages

CNN Part 2

This document discusses pooling layers in convolutional neural networks. It explains that max pooling selects the maximum value in each filter region while average pooling computes the average. Pooling reduces the spatial size and parameters to avoid overfitting. The pooling layer downsamples the input volumes by applying filters with strides while preserving depth. Common applications include LeNet, AlexNet, VGGNet and ResNet.

Uploaded by

pragathisai0912
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
36 views15 pages

CNN Part 2

This document discusses pooling layers in convolutional neural networks. It explains that max pooling selects the maximum value in each filter region while average pooling computes the average. Pooling reduces the spatial size and parameters to avoid overfitting. The pooling layer downsamples the input volumes by applying filters with strides while preserving depth. Common applications include LeNet, AlexNet, VGGNet and ResNet.

Uploaded by

pragathisai0912
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 15

CNN

Max Pooling, Padding


Max Pooling
• Max pooling is a pooling operation that selects the maximum
element from the region of the feature map covered by the filter.
• The output after max-pooling layer would be a feature map
containing the most prominent features of the previous feature
map.
Average Pooling
• Average pooling computes the average of the elements present
in the region of feature map covered by the filter.
• Max pooling gives the most prominent feature in a particular
patch of the feature map, average pooling gives the average of
features present in a patch.
9 9 5
9 9 5
8 6 9
Pooling operation
• The pooling operation involves sliding a two-dimensional filter
over each channel of feature map and summarising the features
lying within the region covered by the filter.
• For a feature map having dimensions nh x nw x nc, the
dimensions of output obtained after a pooling layer is
The Pooling Layer

• Reduce the spatial size


• Reduce the amount of parameters
• Avoid over-fitting

The spatial hyperparameters


• Depth
• Stride
• Zero-padding

VisGraph, HKUST
Pooling layer down-samples the volume spatially, independently in each depth
slice of the input volume.
Left: the input volume of size [224x224x64] is pooled with filter size 2, stride 2
into output volume of size [112x112x64]. Notice that the volume depth is
preserved.
Right: The most common down-sampling operation is max, giving rise to max
pooling, here shown with a stride of 2. That is, each max is taken over 4
numbers (little 2x2 square).
Relation between input size, output size and
filter size
The popular CNN

• LeNet, 1998
• AlexNet, 2012
• VGGNet, 2014
• ResNet, 2015
Applications
• http://yann.lecun.com/exdb/lenet/index.html
• https://d2l.ai/chapter_convolutional-neural-networks/lenet.html
• https://www.kaggle.com/blurredmachine/lenet-architecture-a-compl
ete-guide
• https://d2l.ai/chapter_convolutional-neural-networks/why-conv.html
• https://www.cs.toronto.edu/~lczhang/aps360_20191/lec/w03/convn
et.html
Acknowledgement
• Deep learning –Andrew Ng
• Deep learning-Mitesh M.Khapra
• Ian Goodfellow, YoshuaBengio, Aaron Courville , “Deep Learning”,
The MIT Press, 2016
• Hands-on Mathematics for Deep Learning- Jay Dawani

You might also like