Machine Learning Essentials – Master core ML concepts

Course Curriculum

Chapter 1: Introduction

Lecture 1: Course Overview

Lecture 2: Artificial Intelligence

Lecture 3: Machine Learning

Lecture 4: Deep Learning

Lecture 5: Computer Vision

Lecture 6: Natural Language Processing

Lecture 7: Automatic Speech Recognition

Lecture 8: Reinforcement Learning

Lecture 9: Pre-requisites

Lecture 10: Code Repository

Chapter 2: Supervised vs Unsupervised Learning

Lecture 1: Supervised Learning Introduction

Lecture 2: Supervised Learning Example

Lecture 3: Unsupervised Learning

Chapter 3: Linear Regression

Lecture 1: Introduction to Linear Regression

Lecture 2: Notation

Lecture 3: Hypothesis

Lecture 4: Loss / Error Function

Lecture 5: Training Idea

Lecture 6: Gradient Descent Optimisation

Lecture 7: Gradient Descent Code

Lecture 8: Gradient Descent – for Linear Regression

Lecture 9: The Math of Training

Lecture 10: Code 01 – Data Generation

Lecture 11: Code 02 – Data Normalisation

Lecture 12: Code 03 – Train Test Split

Lecture 13: Code 04 – Modelling

Lecture 14: Code 05 – Predictions

Lecture 15: R2 Score

Lecture 16: Code 06 – Evaluation

Lecture 17: Code 07 – Visualisation

Lecture 18: Code 08 – Trajectory [Optional]

Chapter 4: Linear Regression – Multiple Features

Lecture 1: Introduction

Lecture 2: Hypothesis

Lecture 3: Loss Function

Lecture 4: Training & Gradient Updates

Lecture 5: Code 01 – Data Prep

Lecture 6: Code 02 – Hypothesis

Lecture 7: Code 03 – Loss Function

Lecture 8: Code 04 – Gradient Computation

Lecture 9: Code 05 – Training Loop

Lecture 10: A Note about Shapes

Lecture 11: Code 06 – Evaluation

Lecture 12: Linear Regression using Sk-Learn

Chapter 5: Logistic Regression

Lecture 1: Binary Classification Introduction

Lecture 2: Notation

Lecture 3: Hypothesis Function

Lecture 4: Binary Cross-Entropy / Loss Function

Lecture 5: Gradient Update Rule

Lecture 6: Code 01 – Data Prep

Lecture 7: Code 02 – Hypothesis / Logit Model

Lecture 8: Code 03 – Binary Cross Entropy Loss

Lecture 9: Code 04 – Gradient Computation

Lecture 10: Code 05 – Training Loop

Lecture 11: Code 06 – Visualise Decision Boundary

Lecture 12: Code 07 – Predictions & Accuracy

Lecture 13: Logistic Regression using Sk-Learn

Lecture 14: Multiclass Classification : One Vs Rest

Lecture 15: Multiclass Classification : One Vs One

Chapter 6: Dimensionality Reduction/ Feature Selection

Lecture 1: Curse of Dimensionality

Lecture 2: Feature Selection Vs. Feature Extraction

Lecture 3: Filter Method

Lecture 4: Wrapper Method

Lecture 5: Embedded Method

Lecture 6: Feature Selection – Code

Chapter 7: Principal Component Analysis (PCA)

Lecture 1: Introduction to PCA

Lecture 2: Conceptual Overview of PCA

Lecture 3: Maximising Variance

Lecture 4: Minimising Distances

Lecture 5: Eigen Values & Eigen Vectors

Lecture 6: PCA Summary

Lecture 7: Understanding Eigen Values

Lecture 8: PCA Code

Lecture 9: Choosing the right dimensions

Chapter 8: K-Nearest Neigbours

Lecture 1: Introduction

Lecture 2: KNN Idea

Lecture 3: KNN Data Prep

Lecture 4: KNN Algorithm Code

Lecture 5: Euclidean and Manhattan Distance

Lecture 6: Deciding value of K

Lecture 7: KNN and Data Standardisation

Lecture 8: KNN Pros and Cons

Lecture 9: KNN using Sk-Learn

Chapter 9: PROJECT – Face Recognition

Lecture 1: OpenCV – Working with Images

Lecture 2: OpenCV – Video Input from WebCam

Lecture 3: Object Detection using Haarcascades

Lecture 4: Face Detection in Images

Lecture 5: Face Detection in Live Video

Lecture 6: Face Recognition Project Intro

Lecture 7: Face Recognition 01 – Data Collection