Machine learning

MCQ
1- …. is a subfield of computer science that gives computers the ability to learn without
being explicitly programmed?
a) machine learning
b) DL
c) computer vision
2- In machine learning, data is split into ………… data
a) validation, test
b) train, test
c) train, validation
3- …… concentrates on learning patterns through connecting the relationship between
variables and known outcomes and working with labeled datasets
a) supervised learning
b) unsupervised learning
c) Reinforcement
4- what is ML Category that continuously improves its model by leveraging feedback
from previous iterations?
a) supervised learning
b) unsupervised learning
c) Reinforcement
5- Logistic regression adopts the ……. function to analyze data and predict discrete
classes that exist in a dataset.
a) Sigmoid
b) Tanh
c) relu
6- SVM Uses in
a) Regression
b) Classification
c) Clustering
d) All the above

7- To avoid overfitting problem

a) Choosing one of the fitted polynomial models.
b) Switching to another more complex model class.
c) Thinking differently about the data and start again.
d) all
8- To avoid underfitting. Problem
a) Increase the features.
b) Use another technique.
c) a and b
d) none
9- This neural network is one of the simplest form of ANN, where the data or the input
travels in one direction.
a) FNN
b) CNN
c) FNN
d) SOM
10- Predicting stock prices in the stock market is considered:
a) Regression
 b) Classification
c) None
d) Supervised
11- the classification falls under
a) Supervised machine learning
b) unsupervised machine learning
c) a and b
d) none
12- logistic regression is used in
a) Classification problem
b) Regression problem
c) DL
d) None
13- Which one is the cost function formula
1 (𝑖) 2
a) J(𝜃) = 2𝑚 ∑𝑚 (𝑖)
𝑖=1(ℎ𝜃 (𝑥 ) − 𝑦 )
1
b) J(𝜃) = 2𝑚 ∑𝑚 (𝑖) (𝑖)
𝑖=1(ℎ𝜃 (𝑥 ) – 𝑦 )
2
c) J(𝜃) = ∑𝑚 (𝑖) (𝑖)
𝑖=1(ℎ𝜃 (𝑥 ) + 𝑦 )
14- Which one is the gradient descent formula
𝜕
a) 𝜃𝑗 ≔ 𝜃𝑗 + 𝛼 𝜕𝜃 𝐽(𝜃0 , 𝜃1 )
𝑗
𝜕
b) 𝜃𝑗 ≔ 𝜃𝑗 − 𝛼 𝜕𝜃 𝐽(𝜃0 , 𝜃1 )
𝑗
𝜕
c) 𝜃𝑗 ≔ 𝜃𝑗 − 0.5 ∗ 𝛼 𝐽(𝜃0 , 𝜃1 )
𝜕𝜃𝑗
15- Types of SVM kernel
a) Linear SVC
b) Polynomial SVC
c) Kernel Trick
d) All the above

16- IN this ANN find A1, A2, A3

3.7
1.0 A1
2.9 4.5
3.7
?-5.2
0.0 A2 A3
2.9
-1.5
-4.5 -2.0
1 1

17- A1 =….
a) 0.90
b) 1.2
c) 0.8
d) 1
18- A2 = ….
 a) 0.25
b) 0.32
c) 0.17
d) 0.55
19- A3 = ….
a) 0.76
b) 0.34
c) 1
d) 0.43
20- What are the issues on which biological networks proves to be superior than AI
networks?
a) robustness & fault tolerance
b) flexibility
c) collective computation
d) all of the mentioned

21- The fundamental unit of network is

a) Brain
b) Nucleus
c) Neuron
d) axon
22- What are dendrites?
a) fibers of nerves
b) nuclear projections
c) other name for nucleus
d) none of the mentioned
23- What is shape of dendrites like
a) Oval
b) Round
c) Tree
d) rectangular
24- What kind of learning is involved in pattern clustering task?
a) Supervised
b) Unsupervised
c) learning with critic
d) none of the mentioned
25- In pattern clustering, does physical location of a unit relative to other unit has any
significance?
a) Yes
b) no
c) depends on type of clustering
d) none of the mentioned
26- How is feature mapping network distinct from competitive learning network?
a) geometrical arrangement
b) significance attached to neighbouring units
c) nonlinear units
d) none of the mentioned
27- What is the objective of feature maps?
a) to capture the features in space of input patterns
b) to capture just the input patterns
c) update weights
d) to capture output patterns
 28- How are weights updated in feature maps?
a) updated for winning unit only
b) updated for neighbours of winner only
c) updated for winning unit and its neighbours
d) none of the mentioned
29- In feature maps, when weights are updated for winning unit and its neighbour,
which type learning it is known as?
a) karnaugt learning
b) boltzman learning
c) kohonen’s learning
d) none of the mentioned
30- In self organizing network, how is layer connected to output layer?
a) some are connected
b) all are one to one connected
c) each input unit is connected to each output unit
d) none of the mentioned
31- What is true regarding adaline learning algorithm
a) uses gradient descent to determine the weight vector that leads to minimal error
b) error is defined as MSE between neurons net input and its desired output
this technique allows incremental learning
c) all of the mentioned

32- What is true for competitive learning?

a) nodes compete for inputs
b) process leads to most efficient neural representation of input space
c) typical for unsupervised learning
d) all of the mentioned
True and False
1- A key feature of machine learning is the concept of online-learning (F) self
2- data science is field in computer science and ML is field in Data since (T)
3- Supervised, Unsupervised, Reinforcement is ML Categories (T)
4- The machine must uncover hidden patterns and create labels through the use of
supervised learning algorithms (F) unsupervised
5- When the target variable that we’re trying to predict is continuous we call the
learning problem a regression. (T)
6- When y can take on only a small number of discrete values, we call it a
classification problem. (T)
7- For classification the output is continuous (F) nominal
8- In regression the output is nominal (F) continuous
9- The sigmoid function produces an S-shaped curve that can convert any number
and map it into a numerical value between 2 and 1 (F) 0 & 1
10- Logistic is typically used for binary classification to predict two discrete classes. (T)
11- Large “gap” which led to Decision Trees. (F) SVM
12- SVM learning algorithm is among the best supervised learning algorithm (T)
13- Margin is the distance between the hyperplane and the nearest data point,
multiplied by two. (T)
14- the kernel trick is actually part of SVM. (F) isn't
15- overfitting. refers to a model that can neither model the training data nor generalize
to new data (F) underfitting.
16- underfitting refers to a model that models the training data too well. (F) overfitting
17- Clustering is an unsupervised learning technique (T)
18- Distance between elements in the same cluster is larger than data, and distance
between elements in different clusters is less than data. (F) less, larger
19- ANN is a machine learning approach that models human brain and consists of a
number of artificial neurons. (T)
20- Neural networks consist of one layer of neurons (F) several
21- A typical neural network can be divided into input, and output layers only. (F) input,
hidden, output
22- the cost is the difference between the predicted output and actual output (T)