NOC:Responsible and Safe AI Systems

Lecture 1 - Introduction

Lecture 2 - AI Capabilities - Part 1

Lecture 3 - AI Capabilities - Part 2

Lecture 4 - AI Risk - Part 1

Lecture 5 - AI Risk - Part 2

Lecture 6 - AI Risk - Part 3

Lecture 7 - AI Risk Part 4"Risks associated with AI, getting harmful outputs from AI, biases

Lecture 8 - Robustness - Part 1

Lecture 9 - Robustness - Part 2

Lecture 10 - Robustness Hands-On

Lecture 11 - RLHF

Lecture 12 - AI Alignment

Lecture 13 - Transformers - Part 1

Lecture 14 - Transformers - Part 2

Lecture 15 - Hugging face

Lecture 16 - Unlearning

Lecture 17 - Approximate unlearning

Lecture 18 - Evaluation of Unlearning and Graph Unlearning - Part 1

Lecture 19 - Evaluation of Unlearning and Graph Unlearning - Part 2

Lecture 20 - Representation Engineering - Hands on

Lecture 21 - Introduction to ML - Part 1

Lecture 22 - Introduction to ML - Part 2

Lecture 23 - Basics of Neural Networks and PyTorch - Part 1

Lecture 24 - Basics of Neural Networks and PyTorch - Part 2

Lecture 25 - PyTorch - Basic Workflow

Lecture 26 - PyTorch - Classification

Lecture 27 - Bias - I

Lecture 28 - Bias - II

Lecture 29 - Source of Bias

Lecture 30 - Bias - Handson

Lecture 31 - Bias - III

Lecture 32 - Bias - IV

Lecture 33 - Bias in VLM's

Lecture 34 - Bias Handson - Part 1

Lecture 35 - Bias Handson - Part 2

Lecture 36 - Data Privacy

Lecture 37 - Differential Privacy

Lecture 38 - Approximate Differential Privacy

Lecture 39 - Exponential Mechanism

Lecture 40 - Fairness in Machine Learning

Lecture 41 - Interpretability - I

Lecture 42 - Interpretability - II

Lecture 43 - Interpretability Hands-on - Part 1

Lecture 44 - Interpretability Hands-on - Part 2

Lecture 45 - AI Policies, Regulations, AGI - Part 1

Lecture 46 - AI Policies, Regulations, AGI - Part 2

Lecture 47 - AI Policies, Regulations, AGI - Part 3

Lecture 48 - AI Policies, AGI with Prof. David Krueger - Part 1

Lecture 49 - AI Policies, AGI with Prof. David Krueger - Part 2

Lecture 50 - Finetuning and Jailbreaking: Hands-on

Lecture 51 - AI Governance

Lecture 52 - Research Overview: SaGE- Quantifying moral consistency in LLMs

Lecture 53 - Research Overview: Higher Order Structures for Graph Explanations

Lecture 54 - Research Overview: Representation Surgery

Lecture 55 - Summary - Part 1

Lecture 56 - Summary - Part 2