Syllabus.md

Session 1: Introduction to Machine Learning

Working with Jupyter on Habrok

• Jupyter Notebooks on Habrok
• Jupyter Notebooks on a local machine
• Jupyter Notebooks on Google Colab

What is Machine Learning

• ML vs. Traditional Programming
• Key Concepts in Machine Learning
• Types of Machine Learning

The Machine Learning Workflow

• Data Exploration and Preprocessing
• Model Selection, Training, and Validation
• Model Evaluation

Exploratory Data Analysis (EDA)

• Goals of EDA
• Typical Techniques

Train-Test Split and Cross-Validation

• Train-Test Split
• Cross-Validation

Data Preprocessing

• Handling missing values
• Feature scaling
• Encoding categorical variables

Feature Engineering

• Polynomial
• Derived
• Discretization

Session 2: Supervised Learning - Regression and Evaluation

Simple Linear Regression

• Introduction to Regression
• Simple Linear Regression
• Assumptions of Simple Linear Regression
• Evaluation Metrics

Robust Regression

• Types of Robust Regression
• Huber Robust Regression
• RANSAC Algorithm

Multiple Linear Regression

• Extension of Simple Linear Regression
• Additional Assumption: Low Multicolinearity

Regularized Regression

• Cost Functions
• Gradient Descent
• Regularization
• Ridge and Lasso Regularized Regression

Nonlinearities in Regression

• Polynomial Regression
• Exponential Regression
• Logarithmic Regression

Overfitting, Underfitting, and Hyperparameter Tuning

• Overfitting and Underfitting
• Bias-Variance Tradeoff
• Hyperparameter Tuning

Session 3: Supervised Learning - Classification and Metrics

Introduction to Classification

• Binary vs. Multiclass Classification
• Classification Algorithms
• Decision Boundaries
• Probability vs. Hard Classification
• Output of Classification Models

Classification Basics

• Logistic Regression
• Decision Boundaries

Evaluation Metrics

• Confusion Matrix
• Accuracy, Precision, Recall, F1 Score
• Precision-Recall Tradeoff and Curve
• ROC Curve and AUC

k-Nearest Neighbors (k-NN) and Decision Trees

• The k-NN Algorithm
• Decision Trees
• Information Gain and Gini Index
• Overfitting and Pruning

Support Vector Machines (SVMs)

• Introduction to SVMs
• Linear SVMs
• Nonlinear SVMs
• Kernel Trick

Session 4: Ensemble Methods

Introduction to Ensemble Methods

• What are Ensemble Methods?
• Why Use Ensemble Methods?
• Types of Ensemble Methods

Bagging and Random Forests

• Bagging (Bootstrap Aggregating) Overview
• Random Forests
• Feature Importance in Random Forests

Boosting

• Boosting Overview
• AdaBoost
• Gradient Boosting
• XGBoost

Ensembles of Ensembles

• Stacking
• Multi-level EoE

Session 5: Unsupervised Learning - Clustering and Dimensionality Reduction

Introduction to Unsupervised Learning

• Dimensionality Reduction
• Clustering
• Anomaly Detection

Dimensionality Reduction

• Principal Component Analysis (PCA)
• Autoencoders
• Linear Discriminant Analysis (LDA)

Clustering

• k-Means Clustering
• Hierarchical Clustering

Anomaly Detection

Session 6: Artificial Neural Networks and Deep Learning

Introduction to Neural Networks

• What are Neural Networks?
• Biological Inspiration
• Structure of a Neural Network
• Activation Functions

Training Neural Networks

• Forward Propagation
• Backpropagation
• Loss Functions
• Gradient Descent

Deep Learning

• What is Deep Learning?
• Deep Neural Networks
• Convolutional Neural Networks (CNNs)
• Recurrent Neural Networks (RNNs)
• Autoencoders
• Generative Adversarial Networks (GANs)