Machine Learning for Engineers

Project-based AI for physical systems

An open curriculum for students and instructors who want to do more than run a model: define a physical question, build a defensible baseline, test on meaningful held-out conditions, inspect failure cases, and explain what the result means for an engineering decision.

Originating implementation: MEEG 54403: Machine Learning for Mechanical Engineers at the University of Arkansas. The course is ongoing, and this repository is designed for adaptation by other engineering programs.

Choose your path

I am a…	Start here
Self-directed learner or beginner	Complete the browser-friendly First 30 minutes, then use the learning-path checklist.
Learner who wants a five-minute runnable example	Choose a short code demonstration before opening a full tutorial.
Learner who is unsure which method applies	Use the engineering AI method selector, then confirm the evidence requirements.
Student learning a method	Read the course map, then select a module and complete its tutorial before attempting the assignment.
Engineer bringing a problem or data set	Use the application-studio framework to frame the decision, data rights, baseline, split rule, and validation need before choosing a model.
Instructor adopting one module or a full course	Start with the Instructor Quickstart, then use the adoption guide and instructor guide.
Instructor infusing AI literacy	Start with the engineering AI-literacy framework, then adapt the assignment modes and evidence to your context.
Instructor designing AI-resilient assessment	Start with the assessment and AI policy and shared engineering-ML rubric.
Reader using the proposed book companion	Start with the book companion chapter map.
Reader looking for the evidence base	Browse the reference library and choose a reading path.
Engineer or instructor building AI-enabled engineering practice	Read the engineering AI platform roadmap, then choose the engineering core, agentic workflows, or hardware/deployment pathway.
Contributor	Read the contributing guide, especially the data-rights and student-information boundaries.

Confirmed course implementations and adaptations are listed in IMPLEMENTATIONS.md.

Researchers who want to apply related AI-agent practices to active research can use the companion NED3 Open Engineering AI page to choose between this curriculum and the Mechanical Engineering Research Skill.

Before selecting a module, check module status and learner expectations. It identifies the expected preparation, compute needs, and whether a module is ready to learn, ready to assign, requires a validation refresh, or remains in development.

What makes this different

Engineering question first. Every module connects algorithms to a measurable physical system, variables, units, assumptions, and a decision.
Verification before claims. Students compare against analytical, numerical, or simple empirical baselines and distinguish implementation from validation.
Failure analysis is required. Leakage, domain shift, model-form error, label quality, uncertainty, and visibly wrong predictions are part of the work.
AI is a tool, not evidence of learning. Students may use generative AI only under documented conditions and must verify, explain, and modify their work independently.
Reusable by design. Python is the primary reproducible pathway; modules may be adopted independently with clear provenance and licensing expectations.

Before interpreting any model output, use the shared engineering evidence checklist. It applies across models and forces the same questions about units, baselines, held-out evidence, failures, and AI-assisted work.

Explore the modules

Regression: continuous engineering outcomes, baselines, residuals, and split design.
Classification: image classification, grouped splits, and deployment constraints.
Dimensionality reduction and clustering: structure discovery in boiling images.
Segmentation and object detection: visual labels, transfer learning, and error audits.
Reinforcement learning: bounded sequential decisions and policy evaluation.
Generative models and inverse engineering design: engineering synthetic data, design candidates, and credibility checks (under development).
Time-series forecasting and prognostics: simulated thermal-state forecasting with known heat-load inputs; the boiling sequence extension remains under validation refresh.
Physics-informed neural networks: transient heat conduction, inverse problems, and model-form error.
AI agent harnesses: bounded AI-assisted engineering workflows, skills, MCP, plugins, and independent verification.

All modules now have an accompanying short-code demonstration that exposes one concept, physical check, and modification prompt. The math and short-code authoring guide documents the equation syntax that renders both on GitHub and this website.

Read the curriculum architecture and roadmap for current module readiness, recommended sequencing, and planned industrial-AI extensions.

Evidence and reuse

The repository includes student project examples, a reusable data-card template, a reproducibility checklist, and an engineering AI-literacy framework. The AI-literacy evidence brief distinguishes public guidance, institutional practice, and the limits of the current evidence. Related course and project outcomes are retained as contextual evidence, not as the primary citation.

The preferred scholarly citation is Li et al. (2026). If this curriculum or adapted material informs published or other scholarly work, please cite it; the exportable metadata is in CITATION.cff. Preserve attribution and the BSD 3-Clause license, and do not upload student records, private assessment material, or restricted data.

The project uses a text-first dissemination strategy: maintainable modules, executable short demonstrations, GitHub Pages guides, case-study releases, LinkedIn posts that link back to durable artifacts, and citable papers. See the text-first dissemination strategy for the intended public record and contribution boundaries.