Overview

---

Machine Learning Foundations supports Grade 12 Computer Science in the General framework with 6 worksheets that build understanding of AI ethics, model evaluation, and core machine learning workflows. Students move from data representations (features and labels) to predictive modeling, then connect those ideas to neural networks and modern generative AI. This unit bundle is designed for classroom-ready instruction, with each worksheet targeting a distinct concept and practice task.

What's Included

---

• ✅ AI Ethics and Model Evaluation Worksheet | Grade 12 Computer Science – Examine fairness, bias, and evaluation criteria while interpreting model performance signals.
• ✅ Generative AI and Large Language Models Worksheet | Grade 12 Computer Science – Analyze how large language models generate outputs and what “quality” means in context.
• ✅ Neural Networks and Deep Learning Worksheet | Grade 12 Computer Science – Connect layered representations to learning and describe how deep models improve with data and training.
• ✅ Regression and Prediction from Data to Numbers Worksheet | Grade 12 CS – Use regression ideas to turn data into predictions, focusing on variables and interpretation.
• ✅ Features and Labels Worksheet | Grade 12 Computer Science Machine Learning – Practice creating features and identifying labels for supervised learning tasks.
• ✅ Machine Learning Foundations Data Features and Labels Worksheet | Grade 12 – Strengthen foundational understanding by classifying data into inputs (features) and targets (labels) for model-ready datasets.

Skills & Standards

---

Aligned to the General framework, these worksheets emphasize crosscutting skills such as modeling, analytical reasoning, and evidence-based explanations. Students learn to represent problems with data, describe relationships between inputs and outputs, and justify how evaluation measures relate to real-world decisions. Across the bundle, students practice core disciplinary ideas in computer science and AI: algorithmic systems learn patterns from examples, models can be assessed with appropriate metrics, and the context of deployment shapes what counts as “success.” Learners also build habits of scientific argumentation by interpreting results, recognizing limitations, and explaining conclusions using classroom evidence from each worksheet task.

Perfect For

---

• Teachers seeking structured instruction
• Sub plans
• Homework or review
• Intervention or centers
• Assessment preparation

How to Use

---

Plan for 1–3 weeks of multi-day pacing, using 1 worksheet every 2–3 class periods depending on your schedule and student needs. Start with a short warm-up that previews vocabulary (features, labels, evaluation, prediction). Use guided practice to model how to translate a scenario into a dataset, then complete the worksheet independently with teacher check-ins. Close each session with an exit ticket that requires a brief, evidence-based explanation (for example, which metric best supports a claim about model performance) and use an end-of-unit review to compare predictions, evaluation ideas, and ethical considerations across tasks.

Closing

---

Machine Learning Foundations helps students connect data, modeling, and responsible AI thinking into a cohesive Grade 12 Computer Science experience.

M