YoVDO

Building Our First Simple GAN

Offered By: Aladdin Persson via YouTube

Tags

Generative Adversarial Networks (GAN) Courses Deep Learning Courses Neural Networks Courses Model Evaluation Courses Model Training Courses MNIST Dataset Courses

Course Description

Overview

Learn to build a simple generative adversarial network (GAN) using fully connected layers and train it on the MNIST dataset in this 24-minute video tutorial. Explore the process of constructing both the discriminator and generator components, setting up hyperparameters, initializations, and data preprocessing. Dive into the setup for training GANs, and conclude with hands-on training and evaluation of the model. While the resulting GAN may not be perfect, this tutorial serves as a foundational starting point for implementing more advanced and effective architectures in future lessons.

Syllabus

- Introduction
- Building Discriminator
- Building Generator
- Hyperparameters, initializations, and preprocessing
- Setup training of GANs
- Training and evaluation


Taught by

Aladdin Persson

Related Courses

Neural Networks for Machine Learning
University of Toronto via Coursera Good Brain, Bad Brain: Basics
University of Birmingham via FutureLearn Statistical Learning with R
Stanford University via edX Machine Learning 1—Supervised Learning
Brown University via Udacity Fundamentals of Neuroscience, Part 2: Neurons and Networks
Harvard University via edX