AI-04 · Undergraduate · ENGLISH · PLANNED
Begin with a baseline, trace a model, measure errors and improve it.
Study time is an initial activity estimate, excluding extra reading, revision and extended laboratory or project work. Videos and question bodies have not been produced by adding this outline.
Complete these courses or demonstrate equivalent knowledge. These are recommended prerequisites, not enforced enrolment locks.
YouTube playlist: ARK Artificial Intelligence | Machine Learning I: Supervised Learning
Playlist title reserved in the plan; no YouTube playlist or upload has been created yet.
Sign in to save this learning pathPractical outcome: Predict a synthetic energy-use target and report uncertainty limits.
Explain linear regression model using a visual and one worked real-world example. Context: Predict a synthetic energy-use target and report uncertainty limits. End with a prediction or check-for-understanding.
Explain squared-error loss using a visual and one worked real-world example. Context: Predict a synthetic energy-use target and report uncertainty limits. End with a prediction or check-for-understanding.
Explain gradient descent using a visual and one worked real-world example. Context: Predict a synthetic energy-use target and report uncertainty limits. End with a prediction or check-for-understanding.
Explain feature scaling using a visual and one worked real-world example. Context: Predict a synthetic energy-use target and report uncertainty limits. End with a prediction or check-for-understanding.
Use the first concepts from this section. Predict a synthetic energy-use target and report uncertainty limits. Produce a labelled diagram, trace or calculation; explain each step and check one changed input.
3–6 questions on the preceding first-half concepts only: recall, visual interpretation, application and one plausible misconception. Explain each answer after submission.
Explain polynomial features using a visual and one worked real-world example. Context: Predict a synthetic energy-use target and report uncertainty limits. End with a prediction or check-for-understanding.
Explain ridge regularisation using a visual and one worked real-world example. Context: Predict a synthetic energy-use target and report uncertainty limits. End with a prediction or check-for-understanding.
Explain lasso regularisation using a visual and one worked real-world example. Context: Predict a synthetic energy-use target and report uncertainty limits. End with a prediction or check-for-understanding.
Explain regression diagnostics using a visual and one worked real-world example. Context: Predict a synthetic energy-use target and report uncertainty limits. End with a prediction or check-for-understanding.
Predict a synthetic energy-use target and report uncertainty limits. Work without the example, compare two cases, record assumptions and limitations, then self-review correctness, reasoning and clarity.
6–12 questions covering Linear regression model, Squared-error loss, Gradient descent and the remaining section concepts, with cumulative retrieval from earlier sections. Include a new transfer problem; 70% unlocks progression.
Practical outcome: Compare transparent baselines on an openly licensed toy dataset.
Explain logistic regression using a visual and one worked real-world example. Context: Compare transparent baselines on an openly licensed toy dataset. End with a prediction or check-for-understanding.
Explain decision boundaries using a visual and one worked real-world example. Context: Compare transparent baselines on an openly licensed toy dataset. End with a prediction or check-for-understanding.
Explain k-nearest neighbours using a visual and one worked real-world example. Context: Compare transparent baselines on an openly licensed toy dataset. End with a prediction or check-for-understanding.
Explain naive bayes using a visual and one worked real-world example. Context: Compare transparent baselines on an openly licensed toy dataset. End with a prediction or check-for-understanding.
Use the first concepts from this section. Compare transparent baselines on an openly licensed toy dataset. Produce a labelled diagram, trace or calculation; explain each step and check one changed input.
3–6 questions on the preceding first-half concepts only: recall, visual interpretation, application and one plausible misconception. Explain each answer after submission.
Explain decision trees using a visual and one worked real-world example. Context: Compare transparent baselines on an openly licensed toy dataset. End with a prediction or check-for-understanding.
Explain support vector machines using a visual and one worked real-world example. Context: Compare transparent baselines on an openly licensed toy dataset. End with a prediction or check-for-understanding.
Explain random forests using a visual and one worked real-world example. Context: Compare transparent baselines on an openly licensed toy dataset. End with a prediction or check-for-understanding.
Explain gradient boosting using a visual and one worked real-world example. Context: Compare transparent baselines on an openly licensed toy dataset. End with a prediction or check-for-understanding.
Compare transparent baselines on an openly licensed toy dataset. Work without the example, compare two cases, record assumptions and limitations, then self-review correctness, reasoning and clarity.
6–12 questions covering Logistic regression, Decision boundaries, k-nearest neighbours and the remaining section concepts, with cumulative retrieval from earlier sections. Include a new transfer problem; 70% unlocks progression.
Practical outcome: Choose an evaluation metric from the actual cost of mistakes.
Explain confusion matrix using a visual and one worked real-world example. Context: Choose an evaluation metric from the actual cost of mistakes. End with a prediction or check-for-understanding.
Explain precision using a visual and one worked real-world example. Context: Choose an evaluation metric from the actual cost of mistakes. End with a prediction or check-for-understanding.
Explain recall using a visual and one worked real-world example. Context: Choose an evaluation metric from the actual cost of mistakes. End with a prediction or check-for-understanding.
Explain f1 score using a visual and one worked real-world example. Context: Choose an evaluation metric from the actual cost of mistakes. End with a prediction or check-for-understanding.
Explain roc curves using a visual and one worked real-world example. Context: Choose an evaluation metric from the actual cost of mistakes. End with a prediction or check-for-understanding.
Use the first concepts from this section. Choose an evaluation metric from the actual cost of mistakes. Produce a labelled diagram, trace or calculation; explain each step and check one changed input.
3–6 questions on the preceding first-half concepts only: recall, visual interpretation, application and one plausible misconception. Explain each answer after submission.
Explain precision-recall curves using a visual and one worked real-world example. Context: Choose an evaluation metric from the actual cost of mistakes. End with a prediction or check-for-understanding.
Explain cross-validation using a visual and one worked real-world example. Context: Choose an evaluation metric from the actual cost of mistakes. End with a prediction or check-for-understanding.
Explain hyperparameter search using a visual and one worked real-world example. Context: Choose an evaluation metric from the actual cost of mistakes. End with a prediction or check-for-understanding.
Explain calibration using a visual and one worked real-world example. Context: Choose an evaluation metric from the actual cost of mistakes. End with a prediction or check-for-understanding.
Explain error analysis using a visual and one worked real-world example. Context: Choose an evaluation metric from the actual cost of mistakes. End with a prediction or check-for-understanding.
Choose an evaluation metric from the actual cost of mistakes. Work without the example, compare two cases, record assumptions and limitations, then self-review correctness, reasoning and clarity.
6–12 questions covering Confusion matrix, Precision, Recall and the remaining section concepts, with cumulative retrieval from earlier sections. Include a new transfer problem; 70% unlocks progression.
Combine all three sections: Choose an evaluation metric from the actual cost of mistakes. Submit an original worked artifact, evidence or tests, assumptions and a reflection. Rubric: correctness, method, practical usefulness, reproducibility and communication. Self-reviewed, not certified.
6–12 balanced questions sampling every section of Machine Learning I: Supervised Learning, including interpretation, calculation or reasoning, a misconception and a new application. Passing is 70%; review errors before retrying.
Data experiments, evaluations, model tracing and reproducible projects. Guided work leads to an independent attempt, with a diagram, explanation, trace, calculation or tested artifact. Question bodies are generated when opened in your private learning path. Programming submissions are stored as text; the platform does not execute submitted code.
Use original or appropriately licensed datasets. Practical science activities use models or supplied data unless a qualified supervisor has reviewed a physical experiment.
Open the interactive practice sampler →