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

Macroeconometric Forecasting
International Monetary Fund via edX Machine Learning With Big Data
University of California, San Diego via Coursera Data Science at Scale - Capstone Project
University of Washington via Coursera Structural Equation Model and its Applications | 结构方程模型及其应用 (粤语)
The Chinese University of Hong Kong via Coursera Data Science in Action - Building a Predictive Churn Model
SAP Learning