AI and machine learning interview questions

fit learns parameters from data, such as column means for a scaler.

A neural net stacks layers of weighted sums and nonlinear activations.

Without nonlinear activations, stacked layers collapse into one linear map.

The loss scores how wrong the predictions are, such as cross-entropy for classification.

Regularization penalizes complexity so the model prefers simpler weights or smaller trees.

L2, also called ridge, shrinks weights toward zero but rarely makes them exact zeros.

Dropout randomly turns off units during training so the net cannot rely on any single path.

Cross-validation estimates generalization by training and scoring on several splits of the same data.

You cut the data into k folds, train on k minus one, and score the held-out fold.

Leave-one-out trains almost n models, which is expensive.

Classification predicts a label or class.

Training data fits the model.

The target we want to predict for each example.

It counts true positives, false positives, true negatives, and false negatives.

An input signal the model uses to predict.

Counts of true/false positives and negatives.

The model memorizes training quirks and fails on new data.