We are now familiar with the powerful technique of transfer learning. In this section, we'll discuss some recent and popular network architectures that go beyond the ones we've seen so far. You'll be able to use these networks as pre-trained models in a transfer learning scenario, or if you are brave enough, train them from scratch to solve your tasks.
Advanced network architectures
VGG
The first architecture we're going to discuss is VGG (from Oxford's Visual Geometry Group, https://arxiv.org/abs/1409.1556). It was introduced in 2014, when it became a runner-up in the ImageNet challenge of that year. The VGG family of networks remains popular today and is often used as a benchmark against newer architectures...
