Artificial Intelligence & Machine Learning Program

Week 1. Learn what AI is, history and evolution of AI, Narrow AI, General AI, Super AI, AI vs ML vs Deep Learning, intelligent agents, decision making, Turing Test, rational agents, real-world applications, ethics, bias, and social impact.

Week 2. Learn Python basics, variables, operators, loops, conditions, functions, lambda expressions, data structures, file handling, exception handling, OOP, modules, packages, and virtual environments.

Week 3. Learn arrays, operations, indexing, slicing, iteration, mathematical functions, statistical functions, linear algebra basics, random generation, and vectorization for high performance computing.

Week 4. Learn Series, DataFrames, CSV and Excel import-export, data cleaning, preprocessing, filtering, transformation, GroupBy, aggregation, joins, time series basics, and exploratory data analysis.

Week 5. Learn Matplotlib and Seaborn including line charts, bar charts, scatter plots, histograms, pie charts, customization, subplots, styling, and statistical visualizations.

Week 6. Learn vectors, matrices, probability, statistics, Bayes theorem, calculus, derivatives, gradient descent, eigenvalues, and eigenvectors essential for AI systems.

Week 7. Learn data collection basics, handling missing values, outliers, feature engineering, encoding categorical data, normalization, standardization, train-test split, and reusable data pipelines.

Week 8. Learn supervised vs unsupervised learning, overfitting, underfitting, evaluation basics, and gradient descent concepts.

Week 9. Learn Linear Regression, Logistic Regression, Decision Trees, Random Forest, KNN, Support Vector Machines, Naive Bayes, and Gradient Boosting.

Week 10. Learn clustering using K-Means, Hierarchical, DBSCAN, dimensionality reduction using PCA and t-SNE, anomaly detection, and recommendation systems.

Week 11. Learn agents, environments, rewards, Q-Learning, exploration vs exploitation, and practical real-world reinforcement learning applications.

Week 12. Learn model building, training, evaluation, feature engineering, pipelines, hyperparameter tuning, and model saving/loading.

Week 13. Learn neural networks, activation functions, forward propagation, backpropagation, loss functions, overfitting, and regularization.

Week 14. Learn TensorFlow, Keras, PyTorch basics, model training, evaluation, CNN introduction, RNN introduction, and hyperparameter tuning.

Week 15. Learn image processing basics, CNN image classification, object detection basics, image augmentation, and face recognition systems.

Week 16. Learn text preprocessing, Bag of Words, TF-IDF, embeddings, text classification, sentiment analysis, transformers, and BERT fundamentals.

Week 17. Learn Generative AI concepts, transformer architecture, large language models, prompt engineering, fine-tuning concepts, and using LLM APIs.

Week 18. Learn Retrieval-Augmented Generation, vector databases, AI agents, workflows, multi-agent systems, and LangChain introduction.

Week 19. Learn LangChain, LlamaIndex, OpenAI tools, function calling, workflow automation, and AI API integrations.

Week 20. Learn accuracy, precision, recall, F1-score, cross validation, hyperparameter tuning, bias-variance tradeoff, and imbalanced dataset handling.

Week 21. Learn fairness, bias mitigation, Explainable AI (XAI), data privacy, security, ethics, and AI governance.

Week 22. Learn Pickle, Joblib, Flask, FastAPI, Streamlit, Gradio, Docker basics, cloud deployment, monitoring, and versioning systems.

3-week capstone project where students design, build, evaluate, and deploy a real-world end-to-end AI/ML solution applying all program skills.