A fire-lookout hears that training “walks downhill on the error surface” by taking many small steps instead of solving for weights in one closed equation. Which idea is that?
Select an answer to reveal the explanation.
Short Explanation
Walking downhill on the error surface in many small steps is gradient descent. It is not a one-shot closed-form solve, not label shuffling, and not a cooling choice.
Full Explanation
Gradient descent repeatedly takes a small step that reduces loss. It is not a one-shot closed-form solve, not label shuffling, and not a datacenter cooling choice. Optimizer-variant formulas are not required at this level.