Exponents, Logarithms & Summation Notation — Concept Check
Questions on Exponents, Logarithms & Summation Notation. Exponentials grow explosively, logarithms tame that growth back down, and the Σ (sigma) symbol is just a for-loop — three notations you will meet on every page of AI math.
Questions in this quiz
8 questions on Exponents, Logarithms & Summation Notation — Concept Check. Work through them here, then start the quiz to answer them and see your score.
1.You have a model that outputs probabilities for three classes: [0.8, 0.1, 0.1]. What happens if you take the log of these probabilities?
- AThe values become negative, indicating surprise.
- BThe values become positive, indicating confidence.
- CThe probabilities are squared.
- DThe probabilities are normalized to sum to 1.
2.A neural network outputs a very small probability for the correct class. Why might using log-likelihood be beneficial here?
- AIt increases the probability of the correct class.
- BIt avoids overfitting by reducing model complexity.
- CIt prevents underflow by turning multiplication into addition.
- DIt ensures probabilities sum to 1.
3.Given probabilities [0.7, 0.2, 0.1], what is the result of np.prod(p) compared to np.exp(np.sum(np.log(p)))?
- AThe second is larger due to exponentiation.
- BThe first is larger due to rounding errors.
- CBoth result in the same product value.
- DBoth result in different values due to log transformation.
4.You see the formula Σx_i / n in a paper. How should you interpret it in code?
- AAs a loop that sums elements and divides by their count.
- BAs a loop that sums elements and multiplies by their count.
- CAs a loop that multiplies elements and adds their count.
- DAs a loop that multiplies elements and divides by their count.
5.A model's cross-entropy loss is high. What does this indicate about its predictions?
- AThe predictions are uncertain but correct.
- BThe predictions are confident but incorrect.
- CThe predictions are neither confident nor correct.
- DThe predictions are correct and confident.
6.In a dataset, you compute Σx_i for all i. What does this operation do?
- AIt multiplies all elements in the dataset.
- BIt finds the minimum element in the dataset.
- CIt sums all elements in the dataset.
- DIt finds the maximum element in the dataset.
7.When using softmax, why is e^x used in the formula?
- ATo ensure outputs are negative and sum to 1.
- BTo ensure outputs are positive and sum to 0.
- CTo ensure outputs are positive and sum to 1.
- DTo ensure outputs are negative and sum to 0.
8.What is the relationship between e^x and log(x) in machine learning?
- AThey are both used to increase probabilities.
- BThey are identical operations used interchangeably.
- CThey are unrelated and used for different purposes.
- DThey are inverse operations that undo each other.