Font size
S
M
L
XL
WorksheetsAI&ML--10MINITUES
Total questions: 90
Worksheet time: 15mins
Name
Class
Date
1.
What is the primary goal of Artificial Intelligence (AI)?
a)
To make computers faster
b)
To enable computers to perform tasks requiring human intelligence
c)
To create robots that can mimic human behavior
d)
To develop advanced gaming consoles
2.
Who is regarded as the father of Artificial Intelligence (AI)?
a)
John McCarthy
b)
Marvin Minsky
c)
Alan Turing
d)
Herbert A.
3.
How many primary types of Artificial Intelligence (AI) based on capabilities are discussed in the provided content?
a)
Four
b)
Three
c)
Two
d)
Five
4.
Which type of AI is characterized by its ability to perform a single task with intelligence, such as playing chess or recognizing speech?
a)
Narrow AI
b)
Super AI
c)
Limited Memory AI
d)
Narrow AI
5.
Which type of AI system stores past experiences or data for a short period of time to make decisions?
a)
Reactive Machines
b)
Limited Memory
c)
Theory of Mind
d)
Self-Awareness
6.
What is the purpose of knowledge representation in AI systems?
a)
To help users with complex data structures
b)
To make data storage more efficient
c)
To restrict access to sensitive information
d)
To enable reasoning and decision-making based on stored knowledge
7.
What type of knowledge involves knowing how to perform a sequence of steps or actions?
a)
Procedural Knowledge
b)
Declarative Knowledge
c)
Meta-Knowledge
d)
Episodic Knowledge
8.
Which approach to knowledge representation involves representing knowledge through nodes and links?
a)
Semantic networks
b)
Logical representation
c)
Frames
d)
Production Rules
9.
What type of knowledge refers to the ability to draw logical conclusions or make predictions based on available data?
a)
Declarative Knowledge
b)
Procedural Knowledge
c)
Inferential Knowledge
d)
Meta-Knowledge
10.
Which component of an agent is responsible for detecting changes in the environment?
a)
Actuator
b)
Effector
c)
Sensor
d)
Learning element
11.
What distinguishes model-based reflex agents from simple reflex agents?
a)
Model-based reflex agents consider only the current percept
b)
Model-based reflex agents do not require a fully observable environment
c)
Model-based reflex agents do not rely on an internal model
d)
Model-based reflex agents base their actions solely on percept history
12.
What additional component distinguishes utility-based agents from goal-based agents?
a)
An internal model
b)
A learning element
c)
A critic
d)
A utility function
13.
Which component of a learning agent is responsible for making improvements by learning from the environment?
a)
Critic
b)
Problem generator
c)
Performance element
d)
Learning element
14.
What distinguishes machine learning from artificial intelligence?
a)
Machine learning focuses on simulating human behavior, while AI focuses on learning from data.
b)
AI aims to create intelligent machines, while machine learning specifically allows machines to learn from data.
c)
Machine learning is a broader concept than AI.
d)
AI is solely concerned with maximizing accuracy and patterns.
15.
Which subset of AI is primarily concerned with accuracy and patterns?
a)
Machine learning
b)
Deep learning
c)
Supervised learning
d)
Unsupervised learning
16.
Which type of machine learning is concerned with making accurate predictions based on past data?
a)
Supervised learning
b)
Unsupervised learning
c)
Reinforcement learning
d)
Weak AI
17.
What is the scope of machine learning compared to artificial intelligence?
a)
Machine learning has a broader scope than AI.
b)
Both AI and machine learning have similar scopes.
c)
AI has a wider range of applications than machine learning.
d)
AI is limited in scope compared to machine learning.
18.
What is one primary reason for employing Machine Learning in problem-solving tasks?
a)
Efficiency
b)
Complexity
c)
Infeasibility
d)
Simplicity
19.
Which aspect of traditional programming becomes impractical in complex scenarios, prompting the need for Machine Learning?
a)
Efficiency
b)
Complexity
c)
Infeasibility
d)
Simplicity
20.
In traditional programming, who formulates or codes the rules for processing data?
a)
Machine Learning algorithms
b)
End-users
c)
Programmers
d)
Data analysts
21.
What is a key advantage of Machine Learning over Traditional Programming in terms of rule formulation?
a)
Complexity reduction
b)
Flexibility enhancement
c)
Automatic rule formulation
d)
Improved program performance
22.
What is the typical proportion of data used for training in the train-test set split method?
a)
50% for training and 50% for testing
b)
70-80% for training and 20-30% for testing
c)
90% for training and 10% for testing
d)
95% for training and 5% for testing
23.
What is the purpose of the test dataset in the train-test split evaluation procedure?
a)
To train the machine learning model
b)
To assess the model's performance on unseen data
c)
To fine-tune hyperparameters
d)
To gather more data
24.
Which Python library provides an implementation of the train-test split evaluation procedure?
a)
Scikit-learn
b)
PyTorch
c)
Pandas
d)
Tensorflow
25.
What is the purpose of the random_state parameter in the train_test_split() function?
a)
To specify the proportion of data for testing
b)
To ensure reproducibility of the split
c)
To shuffle the dataset before splitting
d)
To train the machine learning model
26.
What does an overly optimistic estimate of model performance suggest in the train-test split evaluation?
a)
Underfitting
b)
Balanced model
c)
Overfitting
d)
Good generalization
27.
What term describes a machine learning model that is having high bias error?
a)
Overfitting
b)
Underfitting
c)
Balanced model
d)
Good generalization
28.
What is a common reason behind overfitting in machine learning models?
a)
Employing a complex model for a simple problem
b)
Having a large dataset
c)
Fitting the model too tightly to the training data
d)
Using a simple model for a complex problem
29.
What could be a reason for underfitting in machine learning models?
a)
Employing a complex model for a simple problem
b)
Having a large dataset
c)
Fitting the model too tightly to the training data
d)
Using a simple model for a complex problem
30.
What term describes a machine learning model that is having high Variance error?
a)
Overfitting
b)
Underfitting
c)
Balanced model
d)
Good generalization
31.
What is Anaconda primarily used for in the context of data science and machine learning?
a)
Creating interactive web-based environments
b)
Simplifying the management and deployment of programming libraries and tools
c)
Accessing free GPU and TPU resources
d)
Integrating with Google Drive
32.
What is the main advantage of using Google Colab for machine learning tasks?
a)
It simplifies the management and deployment of programming libraries and tools
b)
It offers free access to GPU and TPU resources
c)
It allows users to create and share documents containing live code, equations, and visualizations
d)
It provides seamless integration with Anaconda Navigator
33.
What is the purpose of Jupyter Notebooks in the machine learning workflow?
a)
Installing Anaconda Navigator
b)
Running resource-intensive tasks
c)
Managing and deploying programming libraries and tools
d)
Creating and sharing documents containing live code, visualizations, and narrative text
34.
Which of the following collections in Python is ordered, mutable, and can contain elements of different data types?
a)
Tuple
b)
List
c)
Set
d)
Dictionary
35.
What is the main difference between a list and a tuple in Python?
a)
Lists are mutable, while tuples are immutable
b)
Lists are ordered, while tuples are unordered
c)
Lists are defined using parentheses, while tuples are defined using square brackets
d)
Lists can contain duplicate elements, while tuples contain only unique elements
36.
Which collection type in Python is suitable for storing key-value pairs and is commonly used for tasks involving mapping one piece of data to another?
a)
Tuple
b)
List
c)
Set
d)
Dictionary
37.
What is the primary purpose of NumPy in Python?
a)
Data visualization
b)
Data manipulation and analysis
c)
Scientific computing
d)
Natural language processing
38.
Which library is built on top of NumPy and provides additional functionality for scientific computing tasks?
a)
SciPy
b)
Pandas
c)
Matplotlib
d)
TensorFlow
39.
Which function from SciPy is commonly used for optimization tasks?
a)
optimize_function
b)
optimize
c)
maximize
d)
minimize
40.
What data structure does Pandas provide for working with one-dimensional labeled data?
a)
DataFrame
b)
Array
c)
Series
d)
Matrix
41.
What type of collection does NumPy provide support for?
a)
Lists
b)
Array
c)
Set
d)
Dictionary
42.
Which Python library is described as a versatile 2D plotting library with support for various plot types?
a)
Seaborn
b)
Pandas
c)
Matplotlib
d)
NumPy
43.
Which library provides a high-level interface for creating attractive and informative statistical graphics in Python?
a)
Seaborn
b)
Pandas
c)
Matplotlib
d)
NumPy
44.
What type of plot can be created using Matplotlib's plt.plot() function?
a)
Scatter plot
b)
Histogram
c)
Line plot
d)
Box plot
45.
What type of plot is created using Seaborn's sns.regplot() function?
a)
Scatter plot with a regression line
b)
Histogram
c)
Line plot
d)
Box plot
46.
What is Scikit-learn primarily used for in Python?
a)
Web development
b)
Data analysis and modeling
c)
Game development
d)
Networking
47.
What is used to split the data into training and testing sets in Scikit-learn?
a)
train_test_split function
b)
cross_val_score function
c)
fit function
d)
predict function
48.
What is used to evaluate the performance of a model in Scikit-learn?
a)
plot function
b)
fit function
c)
evaluate function
d)
mean_squared_error function
49.
Which of the following methods is NOT commonly used for data collection in machine learning?
a)
Structured Surveys and Forms
b)
Sensor Data
c)
Genetic Algorithms
d)
Web Scraping
50.
Which type of data consists of numerical values that can take on any value within a certain range?
a)
Discrete Data Type
b)
Continuous Data Type
c)
Binary Data Type
d)
Categorical Data Type
51.
Which step of the data processing cycle involves removing bad data such as redundant or incomplete data?
a)
Data Acquisition
b)
Data Augmentation
c)
Data Preparation
d)
Data Generation
52.
Which of the following is NOT a common dataset split used in machine learning?
a)
Training set
b)
Validation set
c)
Testing set
d)
Evaluation set
53.
When is data augmentation commonly used in machine learning?
a)
To reduce underfitting
b)
To decrease the size of the dataset
c)
To prevent models from overfitting
d)
To increase the computational cost
54.
Which labeling technique involves human annotators manually assigning labels to each data instance?
a)
Semi-Supervised Learning
b)
Transfer Learning
c)
Active Learning
d)
Manual Labeling
55.
What is the purpose of data labeling in machine learning?
a)
To increase the size of the dataset
b)
To assign meaningful and accurate labels to data instances
c)
To remove outliers from the dataset
d)
To reduce data bias
56.
In which type of machine learning, labeled data is typically harder to obtain?
a)
Semi-Supervised Learning
b)
Supervised Learning
c)
Unsupervised Learning
d)
Reinforcement learning
57.
Which technique involves creating modified copies of a dataset using existing data?
a)
Data Acquisition
b)
Data Augmentation
c)
Data Preparation
d)
Data Generation
58.
What problem does imbalanced data pose in machine learning?
a)
It leads to overfitting
b)
It causes bias towards the majority class
c)
It increases model complexity
d)
It results in high computational costs
59.
What is version control?
a)
Managing changes made to files or project folders over time.
b)
Documenting dataset metadata.
c)
Storing and tracking machine learning models.
d)
Analyzing data characteristics and patterns.
60.
What does data documentation include?
a)
Visualization techniques.
b)
Statistical analysis.
c)
Metadata, variable descriptions, and preprocessing steps.
d)
Feature engineering algorithms.
61.
What type of analysis involves exploring relationships between pairs of variables?
a)
Univariate analysis
b)
Bivariate analysis
c)
Multivariate analysis
d)
Descriptive analysis
62.
Which technique is used to convert categorical variables into a numerical format by creating binary columns for each category?
a)
Label Encoding
b)
One-Hot Encoding
c)
Ordinal Encoding
d)
Frequency Encoding
63.
Which library is commonly used for data preprocessing in Python?
a)
Seaborn
b)
Pandas
c)
NumPy
d)
Scipy
64.
What is the purpose of feature scaling in data preprocessing?
a)
To format raw data into an understandable format
b)
To standardize or normalize numerical features
c)
To analyze data for insights
d)
To visualize data effectively
65.
What is the primary focus of data ethics?
a)
Ensuring data accuracy
b)
Establishing data policies
c)
Defining moral principles for data use
d)
Managing data access controls
66.
What does data governance primarily focus on regarding data security?
a)
Ensuring data accuracy
b)
Protecting data from unauthorized access
c)
Establishing data ownership
d)
Defining ethical guidelines for data use
67.
Which of the following best describes supervised learning?
a)
The algorithm studies data to identify patterns without human guidance.
b)
The algorithm learns from labeled data, mapping inputs to desired outputs.
c)
The algorithm explores different options and receives rewards for optimal choices.
d)
The algorithm uses both labeled and unlabeled data to classify unlabeled data.
68.
What key difference distinguishes supervised learning from unsupervised learning?
a)
Supervised learning focuses on regression, while unsupervised learning focuses on classification.
b)
Supervised learning uses labeled data, while unsupervised learning uses unlabeled data.
c)
Supervised learning aims to make predictions, while unsupervised learning aims to discover patterns.
d)
Supervised learning is always deterministic, while unsupervised learning is always stochastic.
69.
In a classification task using supervised learning, the algorithm aims to:
a)
Estimate the relationship between variables.
b)
Identify clusters of similar data points.
c)
Assign new data points to predefined categories.
d)
Learn optimal actions through trial and error.
70.
Which of the following is an example of a supervised learning algorithm?
a)
K-Means clustering
b)
Neural network
c)
Autoencoder
d)
Q-learning
71.
Which of the following is NOT a characteristic of regression analysis?
a)
Models the relationship between dependent and independent variables.
b)
Focuses on predicting continuous values like temperature or salary.
c)
Employs supervised learning with labeled data.
d)
Can be used for classification tasks like spam filtering.
72.
What is the key difference between simple and multiple linear regression?
a)
Multiple linear regression predicts only two categories of outcomes.
b)
Simple linear regression involves both continuous and categorical variables.
c)
Multiple linear regression has only one independent variable.
d)
Simple linear regression can model more complex relationships.
73.
A machine learning algorithm predicts the likelihood of an email being categorized as "urgent," "important," or "regular." Which classification type does this represent?
a)
Binary classification
b)
Multi-class classification with fixed probabilities
c)
Multi-class classification with dynamic probabilities
d)
Hierarchical classification
74.
Which type of clustering assigns each data point to a single, definite cluster?
a)
Soft clustering
b)
Fuzzy clustering
c)
Hierarchically exclusive clustering
d)
Hard clustering
75.
Which of the following is NOT a type of classification?
a)
Binary classification
b)
Multi-class classification
c)
Regression classification
d)
None of the above
76.
What is the main objective of a regression model?
a)
To classify data into different groups
b)
To predict a continuous numerical value
c)
To identify patterns in unlabeled data
d)
To make decisions in an environment to maximize rewards
77.
What is the difference between L1 and L2 regularization?
a)
L1 regularization sets some coefficients to zero, while L2 regularization shrinks them towards zero.
b)
L2 regularization sets some coefficients to zero, while L1 regularization shrinks them towards zero.
c)
They are the same thing.
d)
None of the above
78.
Which of the following is an example of unsupervised learning?
a)
Predicting house prices based on features
b)
Classifying emails as spam or not spam
c)
Grouping customers with similar purchasing behavior
d)
Training an agent to play a game
79.
What type of relationship does linear regression model?
a)
Non-linear relationship
b)
Quadratic relationship
c)
Exponential relationship
d)
Linear relationship
80.
What is the objective of linear regression?
a)
To maximize the error between predicted and actual values
b)
To minimize the error between predicted and actual values
c)
To maximize the coefficient of determination
d)
To minimize the gradient of the cost function
81.
What type of machine learning algorithm is logistic regression?
a)
Supervised learning
b)
Unsupervised learning
c)
Reinforcement learning
d)
Semi-supervised learning
82.
What does the threshold value define in logistic regression?
a)
The range of predicted values
b)
The number of independent variables
c)
The probability of either 0 or 1
d)
The intercept of the regression line
83.
What is one of the primary applications of the K-Nearest Neighbors algorithm?
a)
Clustering
b)
Anomaly detection
c)
Classification
d)
Dimensionality reduction
84.
What is a disadvantage of using a very low value for K in the K-Nearest Neighbors algorithm?
a)
It leads to overfitting
b)
It may be noisy and sensitive to outliers
c)
It requires high computational resources
d)
It requires more training data
85.
Which attribute selection measure is used to calculate the split purity in Decision Trees?
a)
Gini Index
b)
Root Mean Square Error (RMSE)
c)
Mean Absolute Error (MAE)
d)
Information Gain
86.
What is the purpose of pruning in Decision Trees?
a)
Increasing the size of the decision tree
b)
Reducing the size of the decision tree
c)
Balancing the distribution of classes
d)
Improving the accuracy of leaf nodes
87.
Which of the following terms refers to the gap between the hyperplane and the support vectors in SVM?
a)
Margin
b)
Hyperplane
c)
Support Vectors
d)
Kernel function
88.
In SVM, what are the data points that are on or nearest to the hyperplane and influence the position of the hyperplane called?
a)
Margin
b)
Hyperplane
c)
Support Vectors
d)
Kernel function
89.
What theorem forms the basis of Naive Bayes algorithm?
a)
Central Limit Theorem
b)
Pythagoras Theorem
c)
Bayes' Theorem
d)
Fermat's Last Theorem
90.
Which type of Naive Bayes classifier is commonly used for document classification tasks, where binary term occurrence features are used?
a)
Gaussian
b)
Bernoulli
c)
Multinomial
d)
Laplace
Reset
