#
*Machine learning quiz questions TRUE or FALSE with answers, important machine learning interview questions for data science, Top 3 machine learning question set*

##
__Machine Learning TRUE / FALSE Questions - SET 01__

###
*1. Stochastic gradient
descent performs less computation per update than batch gradient descent.*

*1. Stochastic gradient descent performs less computation per update than batch gradient descent.*

(a) TRUE (b)
FALSE

**View Answer**Answer: TRUEStochastic
gradient descent (SGD) computes the gradient using a single sample. For
example, if the training set contains 100 samples then the parameters are
updated 100 times that is one time after every individual example is passed
through the network.Batch gradient
descent computes the gradient using the whole dataset. For example, if the
training dataset contains 100 training examples then the parameters of the
neural network are updated once. |

###
*2. To classify job
applications into two categories and to detect the applicants who lie in their
applications using density estimation to detect outliers we can use generative
classifiers.*

*2. To classify job applications into two categories and to detect the applicants who lie in their applications using density estimation to detect outliers we can use generative classifiers.*

(a) TRUE (b)
FALSE

**View Answer**Answer: TRUEFor the purpose
of density estimation, we need to calculate P(x|y). Hence, we can use
generative classifiers. |

###
*3. A good way to pick
the number of clusters k, used for k-Means clustering is to try multiple values
of k and choose the value that minimizes the distortion measure.*

*3. A good way to pick the number of clusters k, used for k-Means clustering is to try multiple values of k and choose the value that minimizes the distortion measure.*

(a)
TRUE (b) FALSE

**View Answer**Answer: FALSELarge K may be good
for feature representations, but smaller K may be more interpretable. Unfortunately,
there is no single best way to determine K from the data.As the value of K increases, there will be fewer
elements in the cluster. So average distortion will decrease.To find a
satisfactory clustering result, usually, a number of iterations are needed where
the user executes the algorithm with different values of K. The validity of
the clustering result is assessed only visually without applying any formal performance
measures. With this approach, it is difficult for users to evaluate the
clustering result for multi-dimensional data set |

**************************

###
**Related links:**

**Related links:**

## No comments:

## Post a Comment