Completed
Model Uncertainty Application
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
MIT 6.S191 - Deep Learning Limitations and New Frontiers
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 T-shirts! Today!
- 3 Course Schedule
- 4 Final Class Project
- 5 The Rise of Deep Learning
- 6 Power of Neural Nets
- 7 Artificial Intelligence "Hype": Historical Perspective
- 8 Rethinking Generalization
- 9 Capacity of Deep Neural Networks
- 10 Neural Networks as Function Approximators Neural networks are excellent function approximators
- 11 Adversarial Attacks on Neural Networks
- 12 Synthesizing Robust Adversarial Examples
- 13 Neural Network Limitations...
- 14 Why Care About Uncertainty?
- 15 Bayesian Deep Learning for Uncertainty
- 16 Elementwise Dropout for Uncertainty
- 17 Model Uncertainty Application
- 18 Multi-Task Learning Using Uncertainty
- 19 Motivation: Learning to Learn
- 20 AutoML: Learning to Learn
- 21 AutoML: Model Controller At each stes, the model samples a brand new network
- 22 AutoML:The Child Network
- 23 AutoML on the Cloud
- 24 AutoML Spawns a Powerful Idea
