Derivatives & Gradients — Concept Check
Questions on Derivatives & Gradients. A derivative is the slope of a function — how fast the output changes as you nudge the input — and the gradient bundles those slopes for many inputs into the single "uphill" direction that training follows downhill.
Questions in this quiz
8 questions on Derivatives & Gradients — Concept Check. Work through them here, then start the quiz to answer them and see your score.
1.A neural network's loss decreases during training. What does this imply about the gradient?
- AThe gradient is zero, indicating a plateau.
- BThe gradient is irrelevant to the loss function.
- CThe gradient points uphill, and weights are adjusted downhill.
- DThe gradient points downhill, and weights are adjusted uphill.
2.You are checking the numerical derivative of f(x)=x² at x=3 using a small step size. What result should you expect?
- AApproximately 9
- BApproximately 0
- CApproximately 3
- DApproximately 6
3.During gradient descent, you notice the loss function occasionally increases. What might be happening?
- AThe gradient is calculated incorrectly.
- BThe learning rate is too high, causing overshooting.
- CThe model is overfitting the data.
- DThe gradient descent algorithm is not suitable for this problem.
4.For a function f(x, y) = x² + y², what is the gradient at the point (1, 2)?
- A[1, 2]
- B[2, 4]
- C[4, 8]
- D[0, 0]
5.A model's weights are updated using -gradient during training. Why is this done?
- ATo increase the loss function by moving uphill.
- BTo ignore the gradient's direction.
- CTo maintain the current loss function value.
- DTo decrease the loss function by moving downhill.
6.You use a gradient checker and find discrepancies with backpropagation results. What might this indicate?
- AThe gradient checker is unnecessary.
- BThe model is perfectly optimized.
- CErrors in the backpropagation implementation.
- DThe learning rate is too low.
7.What does a zero gradient indicate at a point during optimization?
- AThe function is increasing at that point.
- BThe function is decreasing at that point.
- CThe function is at its global minimum.
- DA local minimum, maximum, or saddle point.
8.A function f(x) has a positive derivative at x=5. What does this imply about f(x) near x=5?
- Af(x) is constant near x=5.
- Bf(x) is increasing near x=5.
- Cf(x) is decreasing near x=5.
- Df(x) has a local maximum at x=5.