You are on page 1of 8

Kernel methods can be used for supervised and unsupervised problems

True

False

Perceptron is _

a single layer feed-forward neural network

an auto-associative neural network

a double layer auto-associative neural network

While running the same algorithm multiple times, which algorithm produces same
results?

Classification Clustering

K Means clustering

Hierarchical clustering

Now Can you make quick guess where Decision tree will fall into _

Unsupervised Learning

Supervised Learning*

The standard approach to supervised learning is to split the set of example into the
training set and the test

True
False

Which technique implicitly defines the class of possible patterns by introducing a


notion of similarity between data?

Linear Regression

Hierarchical clustering

SVM*

Multi-Linear Regression

Kernel

In Kernel trick method, We do not need the coordinates of the data in the feature
space

False

True

What is the benefit of Naïve Bayes ?

Does not require any data

can handle any data volume easily

can process faster with any data

Requires less training data

One has to run through ALL the samples in your training set to do a single update
for a parameter in a particular iteration. This is applicable for

Gradient Descent

Anomaly detection

stochastic gradient descent is wrong

Neural Networks

The model which is widely used for the classification is


Segmentation

Linear Regression

Multi-Linear Regression

Logistic Regression

Which of them, best represents the property of Kernel?

Modularity

Extensibility

Converge

Scalability

Which of the following is not example of Clustering?

Image segmentation

Market segmentation

RFM Analysis

Recommendation engines

Anomaly detection

For which one of these relationships could we use a regression analysis? Chose the
correct one

Relation between age and person is married

Relationship between Height & weight (both Quantitative)

Relationship between being part of committee and number of eye operations

Relationship between eye color (blue/black) and hair color (grey,blonde)

Most famous technique used in Text mining is


Naive Bayes

Segmentation

Clustering

Which model helps SVM to implement the algorithm in high dimensional space?

Classification (I selected this) not sure*

Kernel**

Logistic Regression

Multi-Linear Regression

The main problem with using single regression line??

The main difficulty with using a regression line to analyze these data is ___??

merging of groups

presence of 1 or more outliers

Response variable is not appropriate

Curvilinear data

In a scenario, where the statistical model describes random error or noise instead of
underlying relationship, what happens

Transduction

Underfitting

Probabilistic networks

Overfitting

Objective of unsupervised data covers all these aspect except


low-dimensional representations of the data

prepare the training data set

trace interesting directions in data

find clusters of the data

detect interesting coordinates and correlations

What are different types of Supervised learning

Segmentation and regression

regression and classification

Naive Bayes & classification

Clustering and regression

Which type of the clustering could handle Big Data?

Hierarchical clustering

K Means clustering

Does Logistic regression check for the linear relationship between dependent and
independent variables ?

False

True

Perceptron is _

a single layer feed-forward neural network

an auto-associative neural network

a double layer auto-associative neural network


What are the advantages of neural networks (i) ability to learn by example (ii) fault
tolerant (iii) suited for real time operation due to their high 'computational' rates

(ii) and (iii) are true

(i) and (ii) are true

All the options are correct

(i) and (iii) are true

Which methodology works with clear margins of separation points?

Support Vector Machine

Linear Regression

Logistic Regression

Multi-Linear Regression

Now Can you make quick guess where Decision tree will fall into _

Supervised Learning

Unsupervised Learning

rrelation between two variables

 
The correlation between two variables is given by r = 0.0. . This means

There is a perfect negative relationship between the two variables

The best straight line through the data is horizontal.

All of the points must fall exactly on a horizontal straight line

There is a perfect positive relationship between the two variables is wrong


SVM uses which method for pattern analysis in High dimensional space?

Multi-Linear Regression

Kernel

Logistic Regression

Classification

Correlation and regression are concerned with the relationship between _


quantitative response variable and categorical explanatory variable

2 categorical variables

2 quantitative variables

quantitative explanatory variable and categorical response variable

Consider a regression equation, Now which of the following could not be answered
by regression?
Predict the value of y at a particular value of x

Estimate whether the linear association is positive or negative

Estimate the slope between y and x

Estimate whether the association is linear or non-linear


SVM will not perform well with large data set because (select the best answer)

classification becomes difficult

training time is high

Difficult to simulate model

Lot of noise in data

SVM will not perform well with data with more noise because (select the
best answer)

more work involved in removing noise

training time is high

target classes could overlap

Difficult to simulate model is wrong

SVM will not perform well with data with more noise because (select the best
answer)

more work involved in removing noise

Difficult to simulate model

target classes could overlap**

training time is high

You might also like