Gradient
A set of numbers that tells you which direction to nudge each of a model's weights to reduce the loss, and how strongly. It's the compass that points training downhill toward better predictions.
Think of It Like This
Like feeling the slope under your feet in fog — it tells you which way is downhill and how steep.
Every weight in the model gets its own gradient: a number saying whether nudging that weight up or down would lower the loss, and by how much. The optimizer then takes a small step in the opposite direction of the gradient — that's one increment of learning. Backpropagation is the algorithm that computes all these gradients efficiently in a single backward sweep.