Overview
This course teaches learners how to build a simple generative adversarial network (GAN) using fully connected layers and train it on the MNIST dataset. By following the syllabus, students will achieve the learning outcomes of understanding the architecture of GANs, implementing basic GAN models, setting up training processes, and evaluating the model's performance. The course is designed for individuals interested in delving into the field of deep learning and GANs, particularly beginners looking to gain hands-on experience with building and training neural networks.
Syllabus
- Introduction
- Building Discriminator
- Building Generator
- Hyperparameters, initializations, and preprocessing
- Setup training of GANs
- Training and evaluation
Taught by
Aladdin Persson