Skip to main content

Machine Learning Essentials for AI Engineers

Machine learning essentials are the core ideas behind trained models: learning parameters from data, splitting data into training and test sets, measuring error and recognising overfitting. The unit also explains neural networks and the transformer in plain terms, giving an AI engineer the vocabulary to reason about why models behave as they do.

Stage: Foundations · Part of the AI Engineer roadmap · Last reviewed 19 November 2026

What to learn in Machine Learning Essentials

Machine Learning Essentials interview questions

What does the attention mechanism in a transformer actually compute?

For each token it forms query, key and value vectors, scores the query against every key, normalises the scores with softmax and returns a weighted sum of the values. Each position can therefore pull in information from other positions in parallel, unlike the step-by-step flow of an RNN.

Why is accuracy a poor metric for a fraud detector when 0.5 percent of cases are fraud?

A model that always predicts not fraud scores 99.5 percent accuracy while catching nothing. Precision, recall, F1 or the precision-recall curve show how well the rare class is found, and the decision threshold can be tuned to the relative cost of missed fraud and false alarms.

Where Machine Learning Essentials fits in the AI Engineer roadmap

Machine Learning Essentials belongs to the Foundations stage (beginner level), which takes about 72 hours. What you need before touching models.

Back to the full AI Engineer roadmap