Overview

Machine Learning and Modern AI

This section now includes a lightweight Data Science Foundations layer (EDA, wrangling, regression, basic statistics) in addition to ML lifecycle, modern LLM topics, and responsible AI practices.

1. Foundations

• What is ML? Classical vs Deep Learning
• Intro Statistics for ML
• ML Project Lifecycle

2. Working with Data

• Data: Collection, Labeling, Splits
• Data Wrangling with pandas
• Exploratory Data Analysis (EDA)
• Feature Engineering and Preprocessing

3. Modeling

• Regression Basics
• Training vs Fine-tuning vs Prompting
• NLP and LLMs
• Vision and Multimodal (VLMs)

4. Evaluation & Delivery

• Model Evaluation and Metrics
• Serving and Inference
• MLOps Basics

5. Responsible & Tooling

• Ethics, Bias, and Safety
• Tools and Frameworks

Roadmap (Future Candidates)

Experiment Design & A/B Testing • Advanced Model Validation • Fairness Metrics Deep Dive • Time Series Methods.