Study guides

Artificial Intelligence

2 guides for this subject — how to prepare, what to practise, and how to know it has gone in.

A spoken answer, marked

An examiner's question, answered out loud and marked criterion by criterion. From Artificial Intelligence Viva Questions: Oral Practice Guide.

Oral — Generalisation and overfittingMarked

Examiner

Your training accuracy is 98% but validation accuracy is 71%. Explain what may be happening and what you would investigate first.

2:313:00Mark answer
78%Generalisation and overfitting — marked78/100 · Developing · 2:31 spoken of 3:00
Precise technical explanation16/20

You correctly identified a generalisation gap and described overfitting as fitting noise or training-specific detail.

ImproveState that training and validation performance must be compared using the same metric and relevant preprocessing.

Diagnostic reasoning15/20

You mentioned model complexity and dataset size, but you did not check for leakage or a mismatched validation distribution.

ImproveName leakage, duplicate records, class distribution and train-validation distribution as early checks.

Choice of intervention15/20

You proposed regularisation and more data, both reasonable interventions.

ImproveLink the intervention to the diagnosis: simplify the model or increase regularisation only after confirming the gap is genuine.

Evaluation and limitations15/20

You recommended a validation set but did not explain how to protect the final test set.

ImproveUse validation or cross-validation for choices, then use the untouched test set once for final estimation.

A strong answerThe most likely explanation is overfitting: the model has fitted noise or details specific to the training sample, so it performs poorly on unseen data. First I would check that the metrics are calculated consistently, that preprocessing was fitted only on the training data, and that there is no duplicate record or target leakage. I would also compare the class distribution and feature distribution between the splits. If the gap is genuine, I could collect more representative data, simplify the model, increase regularisation or use early stopping, then select the intervention using validation data and reserve the test set for final evaluation.

Start studying artificial intelligence

Yours are written from your own notes, and the free plan needs no payment details.

Guides

Studying artificial intelligence? Build your artificial intelligence board from your own notes — the cards, papers and lectures are written from it. Free plan: 20 cards, a paper, a lecture and a viva to try.

Start on MySummaries

Other subjects