How deeply does Math and Architectures of Deep Learning cover convolutional block?

Defines the block mathematically and implements its layer sequence, stopping short of detailed training behavior.

Convolutional block

As explained in Math and Architectures of Deep Learning

A repeated network unit composed of one or more convolution layers and a pooling step in the VGG architecture.

A convolutional block is a repeated VGG unit that applies one or more 3 × 3 convolution layers, ReLU activations, and a 2 × 2 max-pooling step. Stacking these blocks builds a convolutional backbone for image classification. section 11.2.1

A block combines:

A ReLU after every convolution, adding nonlinearity while retaining the small-filter design. section 11.2.1

VGG-11 configuration

A VGG-11 backbone uses five blocks: (3, 1, 64), (64, 1, 128), (128, 2, 256), (256, 2, 512), and (512, 2, 512). Each tuple specifies input channels, convolution count, and output features.

How Math and Architectures of Deep Learning covers it

Cover of Math and Architectures of Deep Learning

liveBook manning.com

Read Math and Architectures of Deep Learning on liveBook Get the book at manning.com

Related concepts

VGGpart of · VGG is a family of deep convolutional neural network architectures characterized by stacked layers containing repeated small, typically 3×3, convolutions.
convolutional layerhas part · A convolutional layer is a neural-network layer that applies shared learned filters to local regions of structured input to produce feature representations.
convolutional neural networkpart of · A convolutional neural network is a neural-network architecture that applies learned convolutional operations to extract patterns from structured data.

This explainer was generated by Manning's knowledge graph from the text of Math and Architectures of Deep Learning. The section links point to the parts of the book it draws on.