Modules overview

Module 1: Python Programming for AI & ML (6–7 Days)

Topics:

• Python basics, data types, control flow
• Functions, lambda, map/filter/reduce
• OOP concepts
• File handling, exception handling
• Jupyter & virtual environments
• Flask/FastAPI for ML APIs

Module 2: Data Handling, Analysis & Visualization (7–8 Days)

Topics:

• NumPy, Pandas
• Data cleaning & preprocessing
• Feature inspection
• EDA & visualization
• Web scraping

Module 3: Statistics & Probability for ML (6–7 Days)

Topics:

• Descriptive & inferential statistics
• Probability & Bayes theorem
• Distributions
• Sampling & hypothesis testing

Module 4: EDA & Feature Engineering (5–6 Days)

Topics:

• Data profiling
• Outliers & transformations
• Feature encoding & scaling
• AI-assisted EDA

Module 5: Machine Learning Algorithms (10–12 Days)

Topics:

• Regression & classification
• Model evaluation
• Ensemble learning
• Unsupervised learning
• Recommendation systems

Module 6: Deep Learning & Neural Networks (7–8 Days)

Topics:

• ANN, CNN
• Optimizers & loss functions
• Transfer learning
• Unsupervised learning
• Autoencoders

Module 7: Applied NLP for AI Systems (5–6 Days)

Topics:

• Text preprocessing
• TF-IDF, BoW
• Embeddings
• Transformers overview
• Sentiment analysis

Module 8: Generative AI & LLMs (7–8 Days)

Topics:

• Generative models
• LLM fundamentals
• Prompt engineering
• Text & image generation

Module 9: LLM Apps & RAG (6–7 Days)

Topics:

• LangChain
• Embeddings & vector DBs
• RAG pipelines
• Q&A systems

Module 10: Ethics, Deployment & Capstone (6–7 Days)

Topics:

• Responsible AI
• FastAPI deployment
• Docker basics
• Capstone project