Designing a perfect CNN architecture involves a large amount of experimentation and compute power. Hence, it is often non-trivial to achieve optimal CNN architecture design. Fortunately, a number of CNN architectures exist today that act as a good starting point for many developers and researchers as they wet their feet in designing a CNN network from scratch. In this section, we will go over some popular CNN architectures known today.
Popular CNN architectures
AlexNet
One of the earliest works in popularizing the use of CNNs in large-scale image classification, AlexNet was proposed by Alex Krizhevsky and their co-authors in 2012. It was submitted as an entry to the ImageNet challenge in 2012 and significantly outperformed...
