Section: Lesson 18: Making Stylistic Images with Deep Networks | Kung fu - Machine Learning (FREE version)

Section outline

- Select activity 18.1 Generator vs. Discriminator – Two Parts of Creative AI
  
  · 18.1 Generator vs. Discriminator – Two Parts of Creative AI (Goal: Grasp the two-stage process in AI creativity: a generator proposes outputs and a discriminator judges them.)
- Select activity L18 MT1 FREE content only SCORM12
  
  L18 MT1 FREE content only SCORM12 SCORM package
- Select activity 18.2 Approach 1 – Target Image as the Judge
  
  18.2 Approach 1 – Target Image as the Judge (Goal: Learn the first approach to image generation: using a specific target image as the “discriminator” to guide a generator.)
- Select activity L18 MT2 FREE content only SCORM12
  
  L18 MT2 FREE content only SCORM12 SCORM package
- Select activity 18.3 Approach 2 – Learned Concept as the Judge
  
  18.3 Approach 2 – Learned Concept as the Judge (Goal: Understand the second approach: using a trained classifier (general concept) as the discriminator, instead of one specific image.)
- Select activity L18 MT3 FREE content only SCORM12
  
  L18 MT3 FREE content only SCORM12 SCORM package
- Select activity 18.4 Limits of Fixed Judges and a Hint of Adversarial Training
  
  18.4 Limits of Fixed Judges and a Hint of Adversarial Training (Goal: Recognize the limitations of the above approaches and foreshadow how training a generator and discriminator together (GANs) addresses these issues.)
- Select activity L18 MT4 FREE content only SCORM12
  
  L18 MT4 FREE content only SCORM12 SCORM package