stud
bud
Sign up
Log in
Home
Library
Explore
SAT
More
AIML_Quiz Flashcards | StudBud
Explore
/
AIML_Quiz
AIML_Quiz
50 terms
·
StudBud Administration
·
5 plays
Imported from external platform
Flashcards
50 cards
F
Practice quiz
P
Host live
L
Questions
50
Answers
1
Machine learning means learning from
data.
books.
cars.
machines.
2
Which of the following is a commonly used algorithm in machine learning?
Linear Regression
Quantum Computing
Relational Database Management
Blockchain
3
What is the primary objective of clustering in Unsupervised Learning?
Maximising rewards
Predicting a target variable
Grouping similar data points together
Reducing dimensionality
4
Uninformed search algorithms are called Blind search
False
True
5
What is the primary goal of the Gradient Descent algorithm in machine learning?
To minimize a cost or loss function
To calculate probabilities for classification
To maximize the variance of the data
6
What is a linear regression model?
y=ax+b
y=abx
exponential equation that models the relationship b/w data
a linear equation that models the relationship between data
7
A government agency that supervises the stock market and punishes fraudulent trading practices
FDIC
SEC
HOLC
FHA
8
What is the key difference between informed and uninformed search algorithms?
Informed search avoids the use of cost functions
Informed search uses heuristics to guide the search
Uninformed search requires more memory
9
What is an
Association
in Machine Learning?
identified relationships between various chosen items
data instances grouped together, maximizing similarity
computer models that separate data into distinct classes
self-contained step-by-step operations to be performed
10
In a decision tree Net Gain =
Number of issues shared x Current share price
Initial cost of decision - expected value
Expected value x initial cost of decision
Expected value - initial cost of decision
11
What is the main characteristic of clustering in unsupervised learning?
Clustering automatically groups data points based on similarities.
Clustering is only used for textual data.
Clustering assigns data points to pre-defined categories.
Clustering requires manually labeling each data point.
12
Linear Regression
75
110
96
91
13
A hypotheis is always true.
True
False
14
What is the main difference between regression and classification in supervised learning?
Regression predicts categories, classification predicts continuous numbers
Regression uses unlabeled data, classification uses labeled data
Regression predicts continuous numbers, classification predicts categories
Both terms mean the same thing
15
With Inferencial Statistics we describe the features of data
True
False
16
Informed search algorithms use:
Inadmissible heuristics
Admissible heuristics
No heuristics
Random search strategies
17
What is the purpose of a decision tree in ML?
C. Enhance data visualization
B. Store raw data
D. Predict the future
A. Make decisions based on data
18
In association rule learning, what does support refer to?
The number of transactions in the dataset
The number of transactions containing both items in the rule
The probability of a rule being true
The confidence level of the rule
19
What is another word for hypotheisis
Question
Evaluation
Answer
Prediction
20
Which of these uninformed search algorithms explores the shallowest nodes first?
Iterative Deepening Search
Depth-First Search
Uniform-Cost Search
Breadth-First Search
21
What is classification in supervised learning?
When the AI can find the relationship between two variables
When The AI can make predictions on the pricing of a house.
When the AI can classify certain things into categories
22
Association rule mining is a/an ___ machine learning algorithm
supervised
unsupervised
23
What are rules used for in machine learning?
So it can identify the image
So it knows what can't be in the image
So it can't go out of its boundaries
For outliers
24
Pruning a decision tree results in a smaller decision tree
True
False
25
What is the purpose of the support vector machine (SVM) algorithm in machine learning?
To cluster similar data points
To handle missing values in the dataset
Classify data: Find best hyperplane to separate categories
To perform feature selection in high-dimensional datasets
26
What is Association Rule Mining in machine learning?
A technique to find patterns in a dataset that occur together frequently.
A process to reduce the dimensionality of data.
A method to classify data into predefined categories.
An approach to predict continuous numerical values.
27
In inferencial statistics, parameter is
a characteristic of a sample
a statistic of the sample
a characteristic of the population
a parameter of a statistical function
28
Which statement about uninformed search algorithms is true?
Depth-first search has better space complexity than breadth-first search.
Depth-first search terminates on all state spaces.
None of those.
Breadth-first search has better time complexity than depth-first search.
29
Informed search algorithms are called Heuristic search
True
False
30
Instead of writing code, we feed data to the generic algorithm in Machine learning
False
True
31
Which algorithm is commonly used for clustering in unsupervised learning?
K-Means
Support Vector Machines
Random Forest
Logistic Regression
32
What is clustering in unsupervised learning?
Assigning labels to input data
Grouping similar data points based on features
Training a model with labeled examples
Predicting a continuous output variable
33
What is the difference between simple linear regression and multiple linear regression?
In simple regression, p = 1
In simple regression there are multiple variables
In multiple regression there is only one variable
34
What is the difference between a model and an algorithm in machine learning?
A model is used for training, and an algorithm is used for testing.
There is no difference; the terms are used interchangeably.
An algorithm is a neural network, and a model is a decision tree.
Algorithm:specific set of rules; Model: an instance of an algorithm.
35
What is a hypotheis?
the list of things the scientist needs to experiment
a prediction a scientist makes about what will happen
the steps a scientist follows to perform an experiment
something that is changed in an experiment
36
What is the primary purpose of the 'Random Forest' algorithm in machine learning?
To recursively generate numbers based on a particular rule given as input
To classify data or predict outcomes based on input variables
To encrypt data for cybersecurity
To create digital forests in simulations
37
Which loss is typically used for classification in supervised learning?
Mean squared error loss
Categorical cross-entropy loss
Focal loss
Huber loss
38
Breadth-first search (BFS) is one of the uninformed search algorithms.
True
False
39
When to use the k-mean algorithm in Machine learning ?
Classification
Regression
Labeling
Clustering
40
Standard deviation is an example of what?
Order effect
Measure of central tendency
Interval data
Measure of dispersion
41
Descriptive and Inferencial statistics are the same thing.
True
False
42
What is descriptive statistics?
Explaining the Data
Collecting the Data
Describing the Data
Interpreting the Data
43
Where is decision tree used in?
Classification problem
Clustering problem
Regression problem
Dimensionality Reduction
44
Standard deviation is a measure of:
bad behaviour
the centre
the spread
the outliers
45
Which of the following is not considered as an algorithm in Machine Learning?
Nearest Neighbor
Decision Trees
LISP
Neural Networks
46
K-NN is the best algorithm for classification in supervised learning.
False
True
47
Inferencial statistics is :
There is no such study of statistics
All options are correct
using your sample data to infer some conclusions about your population
summarizing your data; describing your sample.
48
What does a branch represent in a decision tree?
Decision makers
Test of an attribute
A category in the classification
Value of an attribute
49
Decision tree analysis helps in:
None of the above
Estimating supply-demand curves
Understanding market trends
Calculating the expected value of uncertain outcomes
50
K-nearest Neighbor is a parametric algorithm in machine learning.
True
False
