Week 1: Introduction & Python Foundations
Goal: Build a strong base in Python, data handling, and ML logic.
Days 1–6
• Day 1: What is AI, ML, and DL? Real-world use cases
• Day 2: Python for AI — Variables, Loops, Functions
• Day 3: Libraries — NumPy, cv2, ollama, tkinter
• Day 4: Data Cleaning & Preprocessing (handling missing data, encoding)
• Day 5: Exploratory Data Analysis (EDA) using Pandas + Visualization
• Day 6: Mini Project – “House Price Data Analysis”
• Day 7: Review Day / Q&A / Assignment
Week 2: Machine Learning Fundamentals
Goal: Learn core ML algorithms and practice with real data.
Days 8–13
• Day 8: Introduction to Supervised & Unsupervised Learning
• Day 9: Linear Regression — predicting numeric outcome
• Day 10: Logistic Regression — binary classification
• Day 11: Decision Trees & Random Forests
• Day 12: K-Means Clustering & Dimensionality Reduction (PCA)
• Day 13: Mini Project – “Customer Segmentation using K-Means”
• Day 14: Review
Week 3: Deep Learning & Neural Networks
Goal: Understand neural networks and apply TensorFlow/Keras.
Days 15–20
• Day 15: What is Deep Learning? Intro to Neural Networks
• Day 16: TensorFlow & Keras basics (building first model)
• Day 17: Image Classification using CNNs
• Day 18: Activation functions, Optimizers, Loss functions explained
• Day 19: Model evaluation, overfitting, and regularization
• Day 20: Mini Project – “Handwritten Digit Recognition (MNIST)”
• Day 21: Review + Model Improvement Session
Week 4: AI Applications & Final Project
Goal: Apply ML/DL in practical, industry-style projects.
Days 22–27
• Day 22: Natural Language Processing (Text Classification with NLP)
• Day 23: Chatbot or Sentiment Analysis Project
• Day 24: Model Deployment using Streamlit/Flask
• Day 25: AI Ethics, Bias & Responsible AI
• Day 26-29: Final Project Work – Choose one:
1. NLP &LLMS
2. Computer vision project
3. Gamming physic
4. Yolo model
• Day 30: Project Presentation & Feedback
