Online Course – Certified Professional Internship in Google’s Generative Adversarial Networks (GANs), DeepLearning.AI

Internship – 3-part course series

What are GANs?

Generative adversarial networks (GANs) are powerful machine learning models capable of generating realistic output of images, videos, and sounds. GANs have wide applications, including:

• Improving information security
• Data anonymization
• Creating top-notch images
• Colorize black and white photos
• Increasing image resolution
• Creating avatars
• Making 3D images from 2D images

About this internship

DeepLearning.AI’s Generative Affinity Networks (GANs) specialization provides an exciting introduction to image generation using GANs, charting a path from basic concepts to advanced techniques. The specialization also addresses societal implications, including data bias in machine learning.

Build a comprehensive knowledge base and gain hands-on experience with GANs. Train your own model using PyTorch, use it to generate images, and evaluate a variety of advanced GANs.

On you

This internship is designed for software engineers, students, and researchers interested in machine learning and want to understand how GANs work. It provides an accessible path for all levels of learners interested in entering the world of GANs.

Applied Learning Project

• Course 1: Understanding the basic components of GANs, building a basic GAN using PyTorch, using convolutional layers to build DCGANs, implementing the W-Loss function, and building conditional GANs.
• Course 2: Understanding the challenges in evaluating GANs, comparing generative models, using the Fréchet Inception Distance (FID) method, identifying sources of bias and means to locate them, and learning about StyleGAN techniques.
• Course 3: Using GANs for data augmentation and privacy, reviewing additional applications, and building Pix2Pix and CycleGAN for image translation.