Deep Learning Patterns and Practices

7 Alternative connectivity patterns

This chapter covers

• Understanding alternative connectivity patterns for deeper and wider layers
• Increasing accuracy with feature map reuse, further refactoring convolutions, and squeeze-excitation
• Coding alternatively connected models (DenseNet, Xception, SE-Net) with the procedural design pattern

So far, we’ve looked at convolutional networks with deep layers and convolutional networks with wide layers. In particular, we’ve seen how the corresponding connectivity patterns both between and within convolutional blocks addressed issues of vanishing and exploding gradients and the problem of memorization from overcapacity.

Those methods of increasing deep and wide layers, along with regularization (adding ...