Overview
This course teaches learners how to implement Pixel Recurrent Neural Networks for image generation. The course covers three dominant image generation approaches, the architecture of Pixel Recurrent Neural Networks, LSTM equations, and various model architectures. The teaching method involves a theoretical overview followed by practical implementation. This course is intended for individuals interested in deep learning, neural networks, and image generation.
Syllabus
Intro
Outline
Three image generation approaches are dominating the field
Typical Architecture
Kernel mask
Masks
RNN Review
RNN for Image Generation
LSTM Equations
Input-to-State Component
Finished State-to-State Component
Combine State Components
Model Architectures
Taught by
UCF CRCV