# Module 4 Overview

## Theme

Machine learning as empirical inference

## Essential Question

How does learning from data differ from explicit programming?

## Module Components

- `Book prose`: conceptual framing, domain scenario, methods, and failure modes
- `Assignment`: evidence-backed production of a specific artifact
- `Slides`: presentation sequence for seminar or lecture delivery
- `Narration`: spoken version of the slide flow
- `Instructor notes`: facilitation plan, discussion prompts, and grading cues
- `Rubric`: criteria for evaluating the module artifact
- `Notebook`: executable lab aligned with the module theme using synthetic system evidence including task features, model outputs, confidence signals, and review outcomes

## Module Artifact

AI system review package with architecture, evidence, limitations, and deployment recommendation focused on machine learning as empirical inference: Train and compare two baseline models on a small dataset.

## Professional Setting

Students work as if advising an AI review team evaluating a proposed applied AI system before pilot deployment. Their work must be intelligible to technical lead, domain owner, governance reviewer, and end-user representative.