Machine learning quiz questions TRUE or FALSE with answers, important machine learning interview questions for data science, Top 5 machine learning question set
Machine Learning TRUE / FALSE Questions - SET 10
1. A classifier trained on less training data is less likely to overfit.
(a)
TRUE (b) FALSE
View Answer
Answer: FALSE
A specific
classifier (with some fixed model complexity) will be more likely to fit to
the noise in the training data when there is less training data, and is
therefore more likely to overfit.
|
2. Logistic regression cannot be kernelized.
(a)
TRUE (b) FALSE
View Answer
Answer: FALSE
Logistic
regression can be kernelized.
Regular logistic regression
works well for linearly separable data. It’s weakness is with non-linearly
separable data. Kernel logistic regression is a technique that extends
regular logistic regression to deal with data that is not linearly separable.
|
3.
The following product of factors (joint probability computation) corresponds to
a valid Bayesian Network over the variables A, B, C and D: P(A | B) * P(B | C) * P(C | D) * P(D | A).
(a)
TRUE (b) FALSE
View Answer
Answer: FALSE
The Bayesian network as per the given specification is as follows, if you draw a Bayesian network;
The network
generated from the given conditional probabilities results in a cyclic graph.
For a valid Bayesian network, it should be a Directed Acyclic Graph (DAG).
Hence, the given specification does not correspond to a valid Bayesian
network.
Bayesian network
A Bayesian
network is a directed acyclic graph
in which each edge corresponds to a conditional dependency, and each node
corresponds to a unique random variable.
|
**********************
No comments:
Post a Comment