Sign in to confirm you’re not a bot
This helps protect our community. Learn more

MIT 6.S191 (2023): Robust and Trustworthy Deep Learning

Alexander Amini
319K subscribers
94K views 2 years ago
MIT Introduction to Deep Learning 6.S191: Lecture 5 Robust and Trustworthy Deep Learning Lecturer: Sadhana Lolla (Themis AI, https://themisai.io) 2023 Edition For all lectures, slides, and lab materials: http://introtodeeplearning.com​ Lecture Outline 0:00 - Introduction and Themis AI 3:46 - Background 7:29 - Challenges for Robust Deep Learning 8:24 - What is Algorithmic Bias? 14:13 - Class imbalance 16:25 - Latent feature imbalance 20:30 - Debiasing variational autoencoder (DB-VAE) 23:24 - DB-VAE mathematics 27:40 - Uncertainty in deep learning 29:50 - Types of uncertainty in AI 32:48 - Aleatoric vs epistemic uncertainty 33:29  …...more
...more

Introduction and Themis AI

0:00

Background

3:46

Challenges for Robust Deep Learning

7:29

What is Algorithmic Bias?

8:24

Class imbalance

14:13

Latent feature imbalance

16:25

Debiasing variational autoencoder (DB-VAE)

20:30

DB-VAE mathematics

23:24

Uncertainty in deep learning

27:40

Types of uncertainty in AI

29:50

Aleatoric vs epistemic uncertainty

32:48

Estimating aleatoric uncertainty

33:29

Estimating epistemic uncertainty

37:42

Evidential deep learning

44:11

Recap of challenges

46:44

How Themis AI is transforming risk-awareness of AI

47:14

Capsa: Open-source risk-aware AI wrapper

49:30

Unlocking the future of trustworthy AI

51:51
MIT 6.S191 (2023): Robust and Trustworthy Deep Learning
MIT Introduction to Deep Learning 6.S191: Lecture 5 Robust and Trustworthy Deep Learning Lecturer: Sadhana Lolla (Themis AI, https://themisai.io) 2023 Edition For all lectures, slides, and lab materials: http://introtodeeplearning.com​ Lecture Outline 0:00 - Introduction and Themis AI 3:46 - Background 7:29 - Challenges for Robust Deep Learning 8:24 - What is Algorithmic Bias? 14:13 - Class imbalance 16:25 - Latent feature imbalance 20:30 - Debiasing variational autoencoder (DB-VAE) 23:24 - DB-VAE mathematics 27:40 - Uncertainty in deep learning 29:50 - Types of uncertainty in AI 32:48 - Aleatoric vs epistemic uncertainty 33:29 - Estimating aleatoric uncertainty 37:42 - Estimating epistemic uncertainty 44:11 - Evidential deep learning 46:44 - Recap of challenges 47:14 - How Themis AI is transforming risk-awareness of AI 49:30 - Capsa: Open-source risk-aware AI wrapper 51:51 - Unlocking the future of trustworthy AI Subscribe to stay up to date with new deep learning lectures at MIT, or follow us @MITDeepLearning on Twitter and Instagram to stay fully-connected!!

Follow along using the transcript.

Alexander Amini

319K subscribers