M22.1 CONNECT THE MECHANISM
Predicting a label, generating a possibility
One model looks at a doodle and says "cat". Another draws a brand-new cat. From the same twenty doodles, see what each one learns and what only the second can do.
LESSON OVERVIEW14 min lesson
Lesson overview
One model looks at a doodle and says "cat". Another draws a brand-new cat. From the same twenty doodles, see what each one learns and what only the second can do.
What you’ll explore
- Distinguish conditional prediction from generation over possible samples, and identify the role of a latent variable.
GO TO THE SOURCE
Original explanations, connected to the research.
Deep Learning, chapter 20: Deep Generative Models (Goodfellow, Bengio & Courville, 2016)On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes (Ng & Jordan, 2001)GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium (Heusel et al., 2017), which introduced FIDDenoising Diffusion Probabilistic Models (Ho, Jain & Abbeel, 2020)Suggest a correction
A precise note can make an explanation better.
Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.