Answer core ML fundamentals questions

You are given a handful of short ML fundamentals prompts:

1. Give the definitions of precision and recall for a binary classifier and describe how each one ties back to the confusion matrix.
2. With a confusion matrix (TP, FP, TN, FN) supplied, compute both metrics and explain which kinds of mistakes push each one up or down.
3. Answer elementary questions about gradients, such as what a gradient represents and how gradient descent uses it.
4. Talk through typical ensemble learning tradeoffs, for instance bagging versus boosting, bias–variance, and compute/latency.
5. Work through a simple forward pass of a small feed-forward neural network by hand, including matrix multiply, bias, and activation, and state the resulting output.

Overview: This question checks how well a candidate grasps core machine learning fundamentals: precision and recall with confusion-matrix interpretation, gradient concepts in optimization, ensemble tradeoffs, and the mechanics of neural network forward propagation.