High school project idea · Technology & AI
Teach a computer to recognize a narrow visual pattern, then discover how easily confidence can outrun accuracy.
Create a small image-classification prototype using an appropriate tool and evaluate training data, bias, errors, and acceptable use.
Why this project matters
Create a small image-classification prototype using an appropriate tool and evaluate training data, bias, errors, and acceptable use. This project feels different from a school assignment because the student serves users who benefit from classifying a safe, non-sensitive visual category, creates something visible, tests it honestly, responds to feedback, and explains the decisions behind the final result.
What you will create
Use these deliverables as milestones for Build an AI That Can See. Adapt the details to your interests, available time, and real-world opportunities.
Research task definition, class labels, consent, dataset balance, train-test separation, accuracy, confusion matrix, false positives, bias, privacy, and deployment limits. Document the needs, constraints, credible sources, and perspectives of users who benefit from classifying a safe, non-sensitive visual category.
Turn the evidence into a focused plan for the image classification prototype and model card, including success criteria, ethical boundaries, scope, and a realistic path to completion.
Create the first complete version of the image classification prototype and model card. Include a use-case brief, documented dataset, training process, working classifier, evaluation set, error analysis, user interface, model card, and risk review.
test the model on unseen and deliberately difficult examples, compare performance across categories, and observe how users interpret confidence Record what happened, what failed, what users or reviewers said, and which changes you made.
Publish the final image classification prototype and model card with a portfolio-ready case study showing the challenge, evidence, process, revisions, results, limits, and next version.
Make the work stronger
For Build an AI That Can See, use these checkpoints to protect the quality of the work without turning the project into a performance for admissions.
Skills you can build
College application value
Can demonstrate initiative, curiosity, reflection, and growth through the student’s choices, response to setbacks, work with users who benefit from classifying a safe, non-sensitive visual category, and development of Machine Learning, Dataset Design, and Model Evaluation.
The goal of Build an AI That Can See is not to manufacture an impressive activity. Do real work, keep evidence of the process, and reflect honestly on what changed.
Related college majors
Use Build an AI That Can See as a clue, then open a related major guide to compare coursework, career directions, reality checks, and other ways to test the field.
Build an AI That Can See is an original Compass educational starting point designed around real work, visible evidence, feedback, and reflection. It is not an admissions guarantee.