₹1 course

Understand AI, question the output

Learn how models use examples, why testing matters and how to check an AI-generated answer.

Skills you’ll gain:

Supervised ML FundamentalsTrain/Test Dataset SplittingOverfitting DetectionModel Hallucination VerificationIndependent Fact-Checking

Enrol through Razorpay to unlock the lessons after payment confirmation.

Duration & Pacing45–60 Minutes

Self-paced with practical lab tasks

Skill LevelBeginner

General digital literacy

Practical Benchmark60% Case studies & analysis

Hardware wiring & test exercises

VerificationKnowledge Check

Instant feedback with concept analysis

What you’ll learn

Understand feature extraction and how ML models infer decision boundaries from labeled data

Prevent data leakage by rigorously separating training sets from held-out evaluation datasets

Detect fabricated and hallucinatory outputs in generative AI responses with external ground truth

Formulate critical AI evaluation frameworks for classroom and engineering problem solving

Examples, patterns and predictions
25 minsML Core Principles
Explore features, labels, supervised decision boundaries, and why test data must remain unseen.
A confident answer still needs checking
25 minsGenerative AI Evaluation
Audit LLM outputs against datasheets, identify hallucination patterns, and verify claims.

Includes a comprehensive final knowledge check to validate conceptual mastery.

Capstone Hardware Build

Create a structured, verifiable evaluation matrix for auditing generative AI responses against textbook benchmarks.