Overview
This course covers neural network architectures for processing images, focusing on tasks such as classification, segmentation, denoising, blind deconvolution, superresolution, and inpainting. The course teaches Multilayer Perceptrons, Convolutional Neural Networks, Residual Nets, Encoder-decoder nets, and autoencoders. The teaching method includes lectures and discussions on various architectures and their applications in image processing. The course is intended for individuals interested in deep learning, neural networks, and image processing, particularly those looking to enhance their skills in image recognition and manipulation.
Syllabus
Introduction
Multilayer Perceptrons
LexNet
VGGNet
CNNs
Examples
Residual Blocks
SuperResolution
EncoderDecoder
Unit
Autoencoders
Compressive Autoencoders
superresolution autoencoders
sparing nets
MRI reconstruction
Taught by
Paul Hand