CHAPTER 6

Examples of CNN Architectures

We have covered the basic modules in the previous chapters which can be joined together to develop CNN-based deep learning models. Among these modules, we covered convolution, subsampling and several other layers which form large-scale CNN architectures. We noticed that the loss functions are used during training to measure the difference between the predicted and desired outputs from the model. We discussed modules which are used to regularize the networks and optimize their performance and convergence speeds. We also covered several gradient-based learning algorithms for successful CNN training, along with different tricks to achieve stable training of CNNs, such as weight initialization strategies. In ...

Get A Guide to Convolutional Neural Networks for Computer Vision now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.