Artificial Intelligence & Machine Learning

Weekly Syllabus

• Weeks Module 1

  Introduction to AI & ML: History, types (Narrow, General, Super), and real-world applications.

• Weeks Module 2

  Programming Foundations: Python basics, NumPy, SciPy, Pandas, and data visualization.

• Weeks Module 3

  Mathematics for AI & ML: Linear algebra, probability, statistics, calculus, and information theory.

• Weeks Module 4

  Data Handling & Preparation: Data collection, cleaning, feature engineering, and train-test split.

• Weeks Module 5

  Machine Learning Fundamentals: ML workflow, model evaluation, bias-variance tradeoff, and cross-validation.

• Weeks Module 6

  Supervised Learning Algorithms: Regression, decision trees, Random Forest, SVM, k-NN.

• Weeks Module 7

  Unsupervised Learning Algorithms: Clustering (K-means, DBSCAN), dimensionality reduction (PCA).

• Weeks Module 8

  Ensemble & Advanced ML Techniques: Bagging, boosting, XGBoost, and model tuning.

• Weeks Module 9

  Deep Learning Fundamentals: ANNs, activation functions, backpropagation, and optimizers.

• Weeks Module 10

  Deep Learning Architectures: CNNs, RNNs, LSTMs, and Transformers.

• Weeks Module 11

  Natural Language Processing (NLP): Text preprocessing, language models, embeddings, and chatbots.

• Weeks Module 12

  Computer Vision: Image processing, classification, object detection with OpenCV.

• Weeks Module 13

  Reinforcement Learning: MDP, Q-Learning, Deep Q Networks, and applications.

• Weeks Module 14

  Model Deployment & MLOps: APIs, cloud deployment, monitoring, and CI/CD for ML.

• Weeks Module 15

  Ethics, Bias & Responsible AI: Fairness, explainable AI (XAI), privacy, and regulations.

• Weeks Module 16

  Capstone Project: End-to-end AI/ML project from problem definition to deployment.