A convolutional neural network (CNN, ConvNet) is a special kind of neural network that has been applied to a variety of pattern recognition problems, such as computer vision, speech recognition and others.
The architecture of a CNN is designed to take advantage of the 2D structure of an input image or other 2D input such as a speech signal. Unlike a regular neural network, CNN is comprised of one or more convolutional layers and then followed by one or more fully connected layers as in a standard multilayer neural network.
A CNN is has layers to perform four types of operation:
- Rectification (RELU)
- Pooling or Sub Sampling - reduction of the dimensionality of each feature and retaining the most important information
- Classification (Fully Connected Layer) to yield final class output
Best Practices for Convolutional Neural NetworksApplied to Visual Document Analysis
Patrice Y. Simard, Dave Steinkraus and John C. Platt
Gradient-Based Learning Applied to Document Recognition
Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner
Documentaries, videos and podcasts