Lecture
This lecture covers the evolution of convolutional neural networks (CNNs) in image processing, starting from the first CNN trained by backpropagation in 1990 to the deep networks era with AlexNet, GoogleNet, VGGNet, and U-net. It explains the classical neural networks, deep neural networks, training algorithms, and the backpropagation algorithm. The lecture also delves into non-linear steps, efficient implementations, and the forward/backward propagation process in CNNs. Additionally, it discusses different loss functions, the representation of CNNs, software frameworks like TensorFlow, and a comparison of decision surfaces in image processing. The lecture concludes with insights on distribution-free learning, neural networks' performance, and related approaches like radial-basis-function networks and support-vector machines.