Foundations of AI & Machine Learning

Week 1: AI Foundations + Python for ML

1. Day 01: Introduction to AI, ML, Deep Learning, and Data Science – Differences and Real-World Applications
2. Day 02: Python Programming Basics – Variables, Loops, Functions, and Library Setup
3. Day 03: NumPy – Arrays, Mathematical Operations, and Broadcasting
4. Day 04: Pandas – DataFrames, Data Cleaning, GroupBy, and Data Merging
5. Day 05: Data Visualization and Statistics – Matplotlib, Seaborn, Mean, Median, Standard Deviation, Correlation, and Distributions

Week 2: Exploratory Data Analysis + Supervised Learning

1. Day 06: Hands-on: Exploratory Data Analysis Using Titanic/Iris Dataset and GitHub Setup
2. Day 07: Machine Learning Workflow – Train-Test Split, Overfitting, and Bias-Variance Trade-off
3. Day 08: Linear Regression – Concepts and Implementation Using Scikit-learn
4. Day 09: Logistic Regression – Classification, Sigmoid Function, and Decision Boundaries
5. Day 10: Model Evaluation – Accuracy, Precision, Recall, F1-Score, and ROC-AUC

Week 3: Classical Machine Learning Algorithms

1. Day 11: K-Nearest Neighbors (KNN) and Decision Trees
2. Day 12: Random Forest Algorithm and Feature Importance
3. Day 13: Support Vector Machines (SVM) – Kernels and Margins
4. Day 14: Naive Bayes Algorithm and Introduction to Text Classification
5. Day 15: Hands-on: House Price Prediction and Loan Approval Classification Projects

Week 4: Unsupervised Learning + Model Optimization

1. Day 16: K-Means Clustering and Elbow Method
2. Day 17: Hierarchical Clustering and DBSCAN
3. Day 18: Principal Component Analysis (PCA) – Dimensionality Reduction
4. Day 19: Model Optimization – GridSearchCV and Hyperparameter Tuning
5. Day 20: Cross-Validation and Hands-on Customer Segmentation Project

Week 5: Introduction to Deep Learning + Deployment

1. Day 21: Neural Network Fundamentals – Perceptron, Activation Functions, and Backpropagation
2. Day 22: Introduction to TensorFlow/Keras – Building Your First Artificial Neural Network
3. Day 23: Convolutional Neural Networks (CNNs) – Filters, Convolution, and Pooling
4. Day 24: Natural Language Processing (NLP) – Tokenization, TF-IDF, and Introduction to Word Embeddings
5. Day 25: MLOps Fundamentals – Saving and Loading ML Models and Introduction to Streamlit

Week 6: Capstone Project + Career Development

1. Day 26: Capstone Project – Problem Selection, Dataset Collection, and Exploratory Data Analysis
2. Day 27: Capstone Project – Data Preprocessing, Feature Engineering, and Model Development
3. Day 28: Capstone Project – Model Training, Evaluation, and Hyperparameter Tuning
4. Day 29: Model Deployment Using Streamlit, Project Documentation, and GitHub Portfolio
5. Day 30: Final Project Demonstration, Course Revision, Assessment, and AI/ML Career Roadmap