5 Advanced CNN architectures

Welcome to part 2 of this book. Part 1 presented the foundation of neural networks architectures and covered multilayer perceptrons (MLPs) and convolutional neural networks (CNNs). We wrapped up part 1 with strategies to structure your deep neural network projects and tune their hyperparameters to improve network performance. In part 2, we will build on this foundation to develop computer vision (CV) systems that solve complex image classification and object detection problems.

5.1 CNN design patterns

5.2 LeNet-5

5.2.1 LeNet architecture

5.2.2 LeNet-5 implementation in Keras

5.2.3 Setting up the learning hyperparameters

5.2.4 LeNet performance on the MNIST dataset

5.3 AlexNet

5.3.1 AlexNet architecture

5.3.2 Novel features of AlexNet

5.3.3 AlexNet implementation in Keras

5.3.4 Setting up the learning hyperparameters

5.3.5 AlexNet performance

5.4 VGGNet

5.4.1 Novel features of VGGNet

5.4.2 VGGNet configurations

5.4.3 Learning hyperparameters

5.4.4 VGGNet performance

5.5 Inception and GoogLeNet

5.5.1 Novel features of Inception

5.5.2 Inception module: Naive version

5.5.3 Inception module with dimensionality reduction

5.5.4 Inception architecture

5.5.5 GoogLeNet in Keras

5.6 ResNet