Convolutional networks in depth¶

Level 3: CNNs for vision

Coming soon

This page is being written. See the full roadmap for the whole syllabus.

What this chapter will cover¶

Conv, pooling, stride, padding, and dilation
receptive fields
1×1 convolutions
depthwise-separable convolutions
batch norm
architectures from LeNet, AlexNet, VGG, Inception, and ResNet to EfficientNet and ConvNeXt