O'Reilly logo

Computer Vision with Python 3 by Saurabh Kapur

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Convolutional neural networks

Convolutional neural networks (CNNs) were first introduced somewhere around 1998 and since then have evolved a lot. CNNs are a variant of the traditional neural networks, where unlike the neural networks, not all perceptrons are connected to each other. In CNNs, the connections between perceptrons are sparse. Apart from that, each layer in a CNN can behave in a different manner. Let's take an example of a basic CNN and use that as a reference to explain the different concepts involved. The architecture that we will look at is called LeNet, which was proposed by Yann LeCun and others. This research effort was the beginning of the field of CNNs. Let's understand what they are and how they are different from traditional ...

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, interactive tutorials, and more.

Start Free Trial

No credit card required