Convolutional Neural Networks: Filters and Channels

This lecture covers the concept of weight sharing in convolutional neural networks, which allows for shift invariance and generalization of features between different locations in an image. It explains how adding zeros to boundaries maintains the input's dimensionality after convolution. The lecture also discusses the use of different filters and channels, highlighting the learnable parameters and hyper-parameters of convolutional layers. Additionally, it explores various data augmentation techniques such as rotation, cutout, noise addition, and blurring, referencing a framework for contrastive learning of visual representations.