Probability Distributions & the Normal Distribution — Concept Check
Questions on Probability Distributions & the Normal Distribution. A distribution describes how likely each value is; the normal (bell curve) is the default model of natural variation and shows up in weight initialization, noise, and the Central Limit Theorem.
Questions in this quiz
8 questions on Probability Distributions & the Normal Distribution — Concept Check. Work through them here, then start the quiz to answer them and see your score.
1.A data scientist observes that the average of many samples from a skewed distribution forms a bell curve. What principle explains this?
- AUniform Distribution
- BCentral Limit Theorem
- CLaw of Large Numbers
- DBernoulli Distribution
2.In a machine learning model, weights are initialized using a normal distribution with mean 0 and standard deviation 1. Why is this approach used?
- ATo avoid overfitting
- BTo guarantee convergence
- CTo ensure weights are small and centered
- DTo increase model complexity
3.A software engineer uses a uniform distribution to model noise in sensor data. What might be a better model for this noise?
- ANormal distribution
- BExponential distribution
- CBinomial distribution
- DCategorical distribution
4.A team is analyzing the spread of data points around the mean in a dataset. Which parameter of the normal distribution should they focus on?
- AVariance
- BStandard deviation
- CMean
- DMode
5.A developer claims that in a normal distribution, approximately 95% of data lies within 1 standard deviation of the mean. What is the correct range?
- A3 standard deviations
- B2 standard deviations
- C0.5 standard deviations
- D1 standard deviation
6.A neural network's dropout layer uses noise to improve generalization. What distribution is this noise most likely modeled after?
- ABernoulli distribution
- BPoisson distribution
- CUniform distribution
- DNormal distribution
7.A researcher initializes neural network weights using a uniform distribution. What is a potential drawback of this approach compared to using a normal distribution?
- AMay not capture natural variation
- BLeads to deterministic outputs
- CRequires more memory
- DIncreases computation time
8.Why is the normal distribution often used in generative models to map simple noise into complex data?
- AIt naturally models aggregated noise
- BIt simplifies calculations
- CIt is computationally efficient
- DIt is the only continuous distribution