Machine learning quiz questions TRUE or FALSE with answers, important machine learning interview questions for data science, Top 3 machine learning question set, ML exam questions
Machine Learning TRUE / FALSE Questions - SET 13
1. A cumulative distribution function (CDF) cannot be less than 0 or bigger than 1.
(a) TRUE (b) FALSE
|
Answer: TRUE It is a probability function. It can be in the range of 0 to 1. Cumulative Distribution Function (CDF) is a method to describe the distribution of random variables. It can be used to define different kinds of random variables including discrete, continuous, and mixed. |
2. K-Means Clustering is guaranteed to converge (i.e., terminate).
(a) TRUE (b) FALSE
|
Answer: TRUE K-means clustering is guaranteed to converge to a local minimum. Since the loss function is non-negative, the k-means algorithm will eventually converge when the loss function reaches its (local) minimum. |
3. Nearest neighbors is a parametric method.
(a) TRUE (b) FALSE
|
Answer: FALSE Nearest neighbors is a non-parametric method. That is, the method can be used even when the variables are categorical. |
4. K-medoids is a kind of agglomerative clustering.
(a) TRUE (b) FALSE
|
Answer: FALSE K-medoids is a partitioning clustering algorithm. |
5. Performing K-nearest neighbors with K = N yields more complex decision boundaries than 1-nearest neighbor.
(a) TRUE (b) FALSE
|
Answer: FALSE In k nearest neighbors, k=1 increases the complexities. Increasing “k” simplifies decision boundary. K = 1 (complex) K = N: always predict majority class in dataset. (simple) As k increases, we are averaging over more neighbors–the effective decision boundary is more “smooth”. |
No comments:
Post a Comment