Lectures

---

Chapter 18: Learning From Examples

1. Forms of learning
2. Univariate linear regression
3. Activity: Univariate linear regression using Tensorflow Keras
4. Linear classifiers and logistic regression
5. Activity: Logistic regression using tensorflow keras
6. Artificial neural networks
7. Activity: Binary classification using tensorflow keras

Chapter 1: Introduction

1. What is AI?
2. Acting humanly and thinking humanly
3. Thinking rationally and acting rationally
4. Foundations of AI
5. History of AI

Chapter 2: Intelligent Agents

1. Agent function vs agent program (first 20 minutes)
2. Rationality (last 15 minutes)

Chapter 3: Solving Problems by Searching

1. Sample search problems
2. Searching algorithm concepts
3. Uninformed search algorithms
4. Informed search algorithms

Chapter 5: Adversarial Search

1. Introduction to adversarial search
2. Minimax algorithm
3. Alpha-beta pruning algorithm

Chapter 7: Logical Agents

1. Knowledge base agents (logical) and a bit of entailment
2. Entailment

Chapter 22: Natural Language Processing

1. N-gram character models
2. N-grams for language identification
3. How to detect spams using N-grams?
4. Perplexity?
5. BM25 scoring
6. PageRank algorithm

Chapter 24: Perception

1. Edge detection using convolution and smoothing
2. Smoothing an image using convolution
3. Optical flow
4. Image segmentation

Chapter 25: Robotics

1. Types of sensors
2. How does GPS work?
3. Range finders
4. Skip: What is degree of freedom in a robot?
5. Skip: Path planning in moving robots
6. ‘Atlas’ by Boston Dynamics
7. ‘Spot’ by Boston Dynamics

Chapter 26: Philosophy, Ethics, and Safety of AI

Will be posted soon. <!–

1. Can machines really think?
2. Will people lose their sense of being unique?
3. Military robots and future of war
4. The real reason to be afraid of AI

Chapter -1: Fair Artificial Intelligence

Background

Will AI that discriminates based on race, gender, or economic status undermine the public’s confidence in the technology? Seduced by the promise of cost savings and data-driven decision making, organizations will deploy biased systems that end up doing real-world damage. Systems incorporating biased algorithms or trained on biased data will misdiagnose medical patients, bar consumers from loans or insurance, deny parole to reformed convicts, or grant it to unrepentant ones. Biased implementations have raised public backlash as organizations both private and public figure out what AI can and can’t do, and how to use it properly. (source: The Batch)

• The UK recently abandoned an algorithm designed to streamline visa applications after human rights activists sued. The plaintiffs charged that the model discriminated against people from countries with large non-white populations.
• Financial regulators in New York last year launched an investigation into the algorithm behind Apple’s credit card. Users reported that women had received lower interest rates than men with comparable credit ratings.
• The Los Angeles Police Department adopted systems designed to forecast crimes, but it stopped using one and promised to revamp another after determining that they were flawed. Some people identified as high-risk offenders, for instance, had no apparent history of violent crime.

Lectures

1. Algorithmic bias and fairness
2. How AI could reinforce biases in the criminal justice system –>
   

Datasets

---

1. Iris flower dataset data / names
2. Pima diabetes dataset
3. Wine quality dataset