Week Lecture Topic
Module I: Introduction and Exploratory Analysis

1

8/25

 Course Introduction

  • The instructor, the outline, classroom conduct, academic integrity, attendance, and grading policy.

An Introduction to AI and Its History

  • Different Views and Approaches to AI
  • AI vs ML vs DL
  • AI in Industry
  • AI in Enterprise

2

9/1

 Statistical Thinking

  • Basic statistics
  • Graphical exploratory data analysis
  • Quantitative exploratory data analysis
  • Thinking probabilistically (Discrete and Continuous variables)
Module II: Supervised Machine Learning

3

9/8

 EXAM I (Module I)

Introduction to Supervised Learning

  • K-Nearest Neighbor (KNN)
  • Model Generation
  • Train and Test Splitting

4

9/15

 Linear Regression

  • Linear Regression with one variable
  • Model Representation
  • Cost Function
  • Parameter Learning (Gradient Descent)
  • Multivariate Linear Regression
  • Gradient Descent for Multiple Features Normal Equation
  • Polynomial Regression

5

9/22

 Logistic Regression

  • Classification
  • Hypothesis Representation
  • The Problem of Overfitting
  • Decision Boundary
  • Cost Function
  • Advanced Optimization
  • Multiclass Classification

6

9/29*

 **No classes. Monday Classes Meet.

7

10/6

 Support Vector Machines

  • Optimization Objective
  • Large Margin Intuition Kernels
Module III: Unsupervised Machine Learning

8

10/13

 EXAM II (Module II)

Introduction to Unsupervised Learning

  • Clustering with K-Means
  • Hierarchical Agglomerative Clustering
Module IV: Deep Learning

9

10/20

 Introduction to Deep Learning:

  • Neural Networks
  • Convolutional Neural
  • Transfer Learning

10

10/27

 EXAM III (Module III)

Neural Networks: Representation

  • Non-linear Hypotheses
  • Neurons and the Brain
  • Model Representation
  • Example and Intuition
  • Multiclass Classification

11

11/3

 Neural Networks: Learning

  • Learning Cost Function
  • Backpropagation Algorithm
  • Backpropagation Intuition

12

11/10

 Deep Reinforcement Learning

  • Q-Learning
  • Deep Reinforcement Learning
  • Policies and Learning Algorithms
PART IV: Independent Study

13

11/17

 Linear Classifiers in Python

  • Applying Logistic Regression and SVM
  • Loss function

14

11/24**

 **No class. Happy Thanks Given!!

15

12/1

 Linear Classifiers in Python

  • Linear Regression
  • Support Vector Machines

16

12/8

 EXAM IV (Module IV) 
Case Study: School Budgeting with Machine Learning in Python

17

12/15

 Machine Learning Fundamentals with Python | Exam