Sunteți pe pagina 1din 8

CHANDIGARH UNIVERSITY

Gharuan, Mohali

Institute/Department: UNIVERSITY INSTITUTE OF ENGINEERING


División: BLOCK 1
Subject Name: Machine Learning
Subject Code: CSA /ITA-401

Assignment No.: 2
Max. Marks: 12

Assignment Set - 1 Set – 2 Set - 3 Set – 4 Set - 5 Set - 6


Set
Student Concerned Concerned Concerned Concerned Concerned Concerned
List UID's UID's UID's UID's UID's UID's
16BCS1565 16BCS1568 16BCS1572 16BCS1579 16BCS1580 16BCS1598
16BCS1671 16BCS1674 16BCS1677 16BCS1680 16BCS1683 16BCS1685
16BCS1708 16BCS1709 16BCS1760 16BCS1712 16BCS1714 16BCS1719
16BCS1822 16BCS1747 16BCS1839 16BCS1762 16BCS1768 16BCS1770
16BCS1900 16BCS1832 16BCS1924 16BCS1847 16BCS1849 16BCS1851
16BCS1902 16BCS1710 16BCS1927 16BCS1952 16BCS1967

Assignment Set - 7 Set - 8 Set - 9 Set - 10 Set - 11 Set - 12


Set
Student Concerned Concerned Concerned Concerned Concerned Concerned
List UID's UID's UID's UID's UID's UID's
16BCS1599 16BCS1621 16BCS1624 16BCS1629 16BCS1639 16BCS1652
16BCS1692 16BCS1694 16BCS1695 16BCS1698 16BCS1704 16BCS1706
16BCS1728 16BCS1733 16BCS1734 16BCS1735 16BCS1739 16BCS1739
16BCS1780 16BCS1798 16BCS1800 16BCS1806 16BCS1809 16BCS1819
16BCS1852 16BCS1854 16BCS1867 16BCS1872 16BCS1879 16BCS1886
16BCS1970 16BCS1973 16BCS1987 16BCS1811
Course Outcomes:
CO Title Level
Number

CO1 To be able to understand the domain of Machine Learning Remember

CO2 To be able to understand various problem solving techniques of Understand


Machine Learning
CO3 To use the Model algorithms and performing the machine Understand
learning paradigms
CO4 To implements on the basis of all the machine learning paradigms Understand
and techniques
CO5 Compute all the ML algorithms on the basis of performances Understand

CO6 To compute real life problems like supervised and unsupervised Understand

ASSIGNMENT SET 1

Questions:
Sr. No. Question CO Number

1 Explain the Ensemble Methods and their advantages. Gives a CO2


scenario where Ensemble can improve the existing methodology.

2 Give a brief note on the working of random forest algorithm and it’s CO1
applications in various domains with advantages and examples

3 Highlight the working of multi-layer Perceptron with example. CO5


Outline the difference between random forest and decision tree?
4 Explain over fitting issue with random forest? CO1

ASSIGNMENT SET 2

Questions:
Sr. No. Question CO Number

1 Inspect closely and thoroughly the advantages of deep learning over CO2
machine learning?

2 Explain the term ensemble method with example. CO1

3 Highlight following briefly CO3


(i) Present the algorithm for learning decision tree and illustrate the
classification in details.
(ii)You are given a data set. The data set has missing values which
spread along 1 standard deviation from the median. What
percentage of data would remain unaffected? Why
4 Elucidate the situation: CO5
Use the Decision tree to classify the students in the class based on
their academic performance. If You came to know that your model
is suffering from low bias and high variance. Which algorithm
should you use to tackle it? Reason

ASSIGNMENT SET 3

Sr. No. Question CO


Numbe
r

1 Explain the bias-variance decomposition of classification error in CO1


ensemble method with example

2 Describe decision tree learning? What are the problems with replicated CO3
sub-tree and over fitting of model and how to overcome .Explain with
example?
3 Scrutinize the term Back-Propagation in Neural network. CO4

4 Explain the Learning algorithm in Neural network with example. CO5

ASSIGNMENT SET 4

Sr. No. Question CO Number


1 Explain CO1
i.) Examine the problem of replica sub-tree. How to pick
the best splitting attribute.
ii.) Examine the pre pruning and post pruning.

2 Explain CO2
i.) Outline the key revolution in deep learning and describe
its applications.
ii.) Outline the Picking the best splitting attribute: entropy
and information gain
3 Explain the feed-forward deep learning algorithm.. CO3

4 explain some of the different splitting rules used by different CO4


decision tree algorithms.

Set 5

Sr. No. Question CO


Numbe
r

1 State True or False “Because Decision Trees Learn to classify CO1


discrete-valued outputs instead of real valued functions it is impossible
for them to over fit.”
Also explain the term “Occam’s razor.

2
explain the Searching for simple trees and computational complexity
with example
Also explain the over fitting.
3 Describe the over fitting, noisy data, and pruning. Define with the CO3
example of decision tree.
4 Explain Recursive induction of decision trees with example. Also CO4
explain the undercoating.

Set 6
Sr. No. Question CO Number

1 explain the term Gain and Entropy? How is it used to build the CO1
Decision tree in algorithm? Illustrate using an example?
2 Explain the Supervised Learning of Univariate Decision Trees CO2
with example

3 explain the Networks Equivalent to Decision Trees. Explain CO3


Over fitting and Evaluation with example.
4 explain Picking the best splitting attribute in the decision tree CO5
with example

Set 7

Sr. No. Question CO Number

1 Explain the term entropy and information gain with example . CO4

2 Diagrammatically illustrate the basic features of Neural Networks CO2

3 Explain: CO3
Inspect closely and thoroughly steps in Back propagation
algorithm? Why a Multilayer neural network is required?

4 Multilayer perception? How is it trained using Bank CO3


propagation? What is linear separability issue? What is the role
of hidden layer?

Set 8

Sr. No. Question CO Number

1 Outline the Ensemble methods. How ensemble methods are CO5


different from other models

2 Elaborate supervised learning. Define the D-Tree with example. CO3

3 Describe Back-Propagation in Neural network? CO4


4 Elaborate the Searching for simple trees and computational CO1
complexity with example.

Set 9

Sr. No. Question CO Number

1 Elaborate supervised learning. Define the D-Tree with example CO1

2 Describe Recursive inductions of decision trees with example. CO2

3 Outline the key revolution in deep learning and describe its CO3
applications. Explain the feed forward network in deep learning.
4 Define the Supervised Learning of Univariate Decision Trees CO4
with example. What do you mean by Gain and Entropy? How is
it used to build the Decision tree in algorithm? Illustrate using an
example?

Set 10

Sr. No. Question CO Number

1 Describe Back-Propagation in Neural network? CO1

2 Describe Recursive inductions of decision trees with example. CO2

3 Outline the key revolution in deep learning and describe its CO3
applications.
4 Elaborate the Searching for simple trees and computational CO4
complexity with example

Set 11

Sr. No. Question CO Number


1 Outline the Ensemble methods. How ensemble methods are CO1
different from other models

2 Outline the key revolution in deep learning and describe its CO2
applications. Explain the feed forward network in deep learning.

3 The Supervised Learning of Univariate Decision Trees with CO3


example. What do you mean by Gain and Entropy? How is it
used to build the Decision tree in algorithm? Illustrate using
an example.

4 Illustrate Picking the best splitting attribute in the decision tree CO4
with example

Set 12

Sr. No. Question CO Number

1 CO4
Outline the Networks Equivalent to Decision Trees. Explain Over
fitting and Evaluation with example.

2 Explain Ensemble Methods and their advantages. Gives a CO2


scenario where Ensemble can improve the existing methodology

3 Write a brie note on the working of random forest algorithm and CO3
it’s applications in various domains with advantages and examples
and outline the difference between the d-tree and random forest.

4 Outline the key revolution in deep learning and describe its CO1
applications. Explain the feed forward network in deep learning.

S-ar putea să vă placă și