CNN Overview
Introduction
Read this: Convolution Neural Network by cs231n

Example of simple CNN architecture


LeNet-5 (1998): image by Raimi Karim

AlexNet(2012)

VGG-16(2014)

Convolution
Activation Function
Pooling
A problem with the output feature maps is that they are sensitive to the location of the features in the input. One approach to address this sensitivity is to down sample the feature maps. This has the effect of making the resulting down sampled feature maps more robust to changes in the position of the feature in the image, referred to by the technical phrase ālocal translation invariance.ā
Read this: Introduction to Pooling Layers by Machine Learning Mastery
Fully Connected Layer
LeNet-5
LeNet-5 is one of the simplest architectures. It has 2 convolutional and 3 fully-connected layers (hence ā5ā ā it is very common for the names of neural networks to be derived from the number of convolutional and fully connected layers that they have). The average-pooling layer as we know it now was called a sub-sampling layer and it had trainable weights (which isnāt the current practice of designing CNNs nowadays). This architecture has about 60,000 parameters.
āļøWhatās novel?
This architecture has become the standard ātemplateā: stacking convolutions with activation function, and pooling layers, and ending the network with one or more fully-connected layers.
šPublication
Authors: Yann LeCun, LƩon Bottou, Yoshua Bengio, and Patrick Haffner
Published in: _**_Proceedings of the IEEE (1998)
Last updated
Was this helpful?