A quarry wants a rockfall-risk score. Plan A feeds four engineered numbers (slope angle, overnight rain, blast count, crack width) into a random forest. Plan B feeds raw geophone waveforms into a multi-layer network that learns its own features. Which pairing is accurate?
Select an answer to reveal the explanation.
Short Explanation
Think of Plan A like a clerk with four filled-in boxes, and Plan B like someone who listens to the raw rumble and learns what trouble sounds like. A random forest on slope, rain, blasts, and crack width is classical machine learning on engineered numbers. A multi-layer net on geophone waveforms is a neural network chewing unstructured signal, not a generative model just because it outputs a score.
Full Explanation
Classical machine learning typically consumes a small set of engineered features, which is Plan A. A neural network can learn representations from raw unstructured signal such as waveforms, which is Plan B. A numeric risk score is a prediction, not generative AI. Using historical numbers does not make a random forest deep learning. Waveforms are a standard input to neural networks, not something that requires a printed checklist.