CPE 126 INTRODUCTION TO ARTIFICIAL INTELLIGENCE
COMPLETE REVIEWER |QUESTIONS & ANSWERS + MACHINE
LEARNING, LINEAR ALGEBRA, NUMPY & PYTHON | MAPÚA
UNIVERSITY
148 Questions with Answers and Detailed Rationales
100 PERCENT GUARANTEED PASS
INSTANT DOWNLOAD ANSWERS INCLUDED
IMPORTANCE OF THIS DOCUMENT
This comprehensive examination preparation guide has been meticulously developed to help you succeed in the
CPE 126 INTRODUCTION TO ARTIFICIAL INTELLIGENCE COMPLETE REVIEWER |QUESTIONS &
ANSWERS + MACHINE LEARNING, LINEAR ALGEBRA, NUMPY & PYTHON | MAPÚA UNIVERSITY. It
contains 148 carefully selected questions that reflect the most current exam content and testing strategies. Each
question is accompanied by a correct answer and a detailed rationale that explains the underlying
pathophysiology, pharmacology, or clinical reasoning.
Self-Assessment – Test your knowledge and Exam Preparation – Familiarize yourself with the
identify areas requiring further question format and content
study areas
Concept Reinforcement – Deepen your Confidence Building – Develop test-taking
understanding through strategies and reduce
evidence-based exam anxiety
rationales
Time Management – Practice answering
questions under simulated
exam conditions
Review Summary 148 Questions
Foundations - Application - CPE 126 Introduction TO Artificial Intelligence Complete Reviewer & Machine
Learning Linear Algebra Numpy & Python MAP A University Introduction TO Artificial Intelligence Machine
Learning Linear Algebra Numpy & Python Undergraduate YEAR 2-3 Sophomore/junior MAP A University
CPE Program
All answers with rationales
,Table of Contents
Content Area Questions Key Topics
Introduction TO Artificial 1-25 Agent, Numpy, Array, State, Accuracy
Intelligence
Intelligent Agents AND 26-50 Learning, Model, Matrix, Classifier, Accuracy
Environments
Problem Solving AND Search 51-75 Matrix, Numpy, Array, Shape, Supervised
Algorithms
Machine Learning 76-100 Search, Numpy, Array, Shape, Learning
Fundamentals
Supervised Learning 101-125 Numpy, Learning, Array, Matrix, Python
Algorithms
Unsupervised Learning 126-148 Correctly, Linear, Dataset, Model, Matrix
Algorithms
TOTAL 148 All questions include answers and detailed rationales
,Section A - Introduction TO Artificial Intelligence
Q1.
An agent operating in a partially observable, stochastic environment with continuous
state and action spaces is BEST modeled as which type of agent?
A. Simple reflex agent B. Model-based reflex agent
C. Utility-based learning agent D. Goal-based agent with perfect
information
Correct: C - Utility-based learning agent
Rationale:Partially observable, stochastic, continuous environments demand agents that
maintain internal state, reason under uncertainty, and optimize expected utility while learning
from experience - hallmarks of a utility-based learning agent. Simple and model-based reflex
agents lack utility optimization under uncertainty, and perfect-information goal-based agents
cannot handle partial observability.
Why the other answers are wrong:
A. Simple reflex agents respond only to current percepts and cannot handle partial
observability or stochasticity.
B. Model-based reflex agents track state but do not optimize utility or learn from stochastic
outcomes.
D. Perfect-information assumption contradicts the partially observable environment described.
Reference: Russell, S. & Norvig, P. (2021). Artificial Intelligence: A Modern Approach, 4th Ed., Ch. 2.
Q2.
Given matrix A = [[2, 0], [0, 3]], which statement correctly describes its eigenvalues and
eigenvectors?
A. Eigenvalues 2 and 3; eigenvectors along B. Eigenvalues 5 and 1; eigenvectors [1,1]
coordinate axes and [1,-1]
C. Eigenvalues 2 and 3; eigenvectors [1,1] D. Eigenvalues 6 and 1; eigenvectors along
and [1,-1] coordinate axes
Correct: A - Eigenvalues 2 and 3; eigenvectors along coordinate axes
Rationale:For a diagonal matrix, eigenvalues are the diagonal entries (2 and 3) and
eigenvectors are the standard basis vectors e1 and e2. Off-diagonal zeros mean no rotation
of eigenbasis, so eigenvectors lie along coordinate axes.
Why the other answers are wrong:
B. The eigenvalues of a diagonal matrix are its diagonal entries, not 5 and 1.
C. Eigenvectors [1,1] and [1,-1] correspond to a different matrix (e.g., [[4,2],[2,4]]).
Page 3
, Section A - Introduction TO Artificial Intelligence
D. Eigenvalues are not products of diagonal entries; 6 is incorrect.
Reference: Strang, G. (2023). Introduction to Linear Algebra, 6th Ed., Ch. 6.
Q3.
In NumPy, what is the output shape of `np.arange(12).reshape(3,4)[:, 1:3].sum(axis=0)`?
A. Scalar B. Shape (2,)
C. Shape (3,) D. Shape (3,2)
Correct: B - Shape (2,)
Rationale:Slicing `[:, 1:3]` yields a (3,2) array; summing along axis=0 collapses rows,
producing a shape (2,) vector. Axis=0 sums over rows, leaving columns.
Why the other answers are wrong:
A. A scalar results only if summing over all axes or using .sum() without axis.
C. Shape (3,) would result from summing axis=1, not axis=0.
D. Shape (3,2) is the pre-sum slice shape, not post-reduction.
Reference: McKinney, W. (2022). Python for Data Analysis, 3rd Ed., Ch. 4 (NumPy Basics).
Q4.
A spam filter trained on 10,000 labeled emails achieves 99% training accuracy but 72% test
accuracy. Which remedy is MOST appropriate?
A. Increase model complexity with more B. Apply regularization and gather more
hidden layers training data
C. Reduce the test set size to lower D. Switch from supervised to unsupervised
variance learning
Correct: B - Apply regularization and gather more training data
Rationale:The large train-test gap signals overfitting; regularization (L1/L2, dropout) and
more data reduce variance. Increasing complexity worsens overfitting, and switching
paradigms is unwarranted when labels exist.
Why the other answers are wrong:
A. More complexity increases overfitting, widening the train-test gap.
C. Shrinking the test set reduces evaluation reliability, not model generalization.
D. Unsupervised learning discards label information and is inappropriate for spam
classification.
Reference: Géron, A. (2022). Hands-On Machine Learning, 3rd Ed., Ch. 4.
Page 4
COMPLETE REVIEWER |QUESTIONS & ANSWERS + MACHINE
LEARNING, LINEAR ALGEBRA, NUMPY & PYTHON | MAPÚA
UNIVERSITY
148 Questions with Answers and Detailed Rationales
100 PERCENT GUARANTEED PASS
INSTANT DOWNLOAD ANSWERS INCLUDED
IMPORTANCE OF THIS DOCUMENT
This comprehensive examination preparation guide has been meticulously developed to help you succeed in the
CPE 126 INTRODUCTION TO ARTIFICIAL INTELLIGENCE COMPLETE REVIEWER |QUESTIONS &
ANSWERS + MACHINE LEARNING, LINEAR ALGEBRA, NUMPY & PYTHON | MAPÚA UNIVERSITY. It
contains 148 carefully selected questions that reflect the most current exam content and testing strategies. Each
question is accompanied by a correct answer and a detailed rationale that explains the underlying
pathophysiology, pharmacology, or clinical reasoning.
Self-Assessment – Test your knowledge and Exam Preparation – Familiarize yourself with the
identify areas requiring further question format and content
study areas
Concept Reinforcement – Deepen your Confidence Building – Develop test-taking
understanding through strategies and reduce
evidence-based exam anxiety
rationales
Time Management – Practice answering
questions under simulated
exam conditions
Review Summary 148 Questions
Foundations - Application - CPE 126 Introduction TO Artificial Intelligence Complete Reviewer & Machine
Learning Linear Algebra Numpy & Python MAP A University Introduction TO Artificial Intelligence Machine
Learning Linear Algebra Numpy & Python Undergraduate YEAR 2-3 Sophomore/junior MAP A University
CPE Program
All answers with rationales
,Table of Contents
Content Area Questions Key Topics
Introduction TO Artificial 1-25 Agent, Numpy, Array, State, Accuracy
Intelligence
Intelligent Agents AND 26-50 Learning, Model, Matrix, Classifier, Accuracy
Environments
Problem Solving AND Search 51-75 Matrix, Numpy, Array, Shape, Supervised
Algorithms
Machine Learning 76-100 Search, Numpy, Array, Shape, Learning
Fundamentals
Supervised Learning 101-125 Numpy, Learning, Array, Matrix, Python
Algorithms
Unsupervised Learning 126-148 Correctly, Linear, Dataset, Model, Matrix
Algorithms
TOTAL 148 All questions include answers and detailed rationales
,Section A - Introduction TO Artificial Intelligence
Q1.
An agent operating in a partially observable, stochastic environment with continuous
state and action spaces is BEST modeled as which type of agent?
A. Simple reflex agent B. Model-based reflex agent
C. Utility-based learning agent D. Goal-based agent with perfect
information
Correct: C - Utility-based learning agent
Rationale:Partially observable, stochastic, continuous environments demand agents that
maintain internal state, reason under uncertainty, and optimize expected utility while learning
from experience - hallmarks of a utility-based learning agent. Simple and model-based reflex
agents lack utility optimization under uncertainty, and perfect-information goal-based agents
cannot handle partial observability.
Why the other answers are wrong:
A. Simple reflex agents respond only to current percepts and cannot handle partial
observability or stochasticity.
B. Model-based reflex agents track state but do not optimize utility or learn from stochastic
outcomes.
D. Perfect-information assumption contradicts the partially observable environment described.
Reference: Russell, S. & Norvig, P. (2021). Artificial Intelligence: A Modern Approach, 4th Ed., Ch. 2.
Q2.
Given matrix A = [[2, 0], [0, 3]], which statement correctly describes its eigenvalues and
eigenvectors?
A. Eigenvalues 2 and 3; eigenvectors along B. Eigenvalues 5 and 1; eigenvectors [1,1]
coordinate axes and [1,-1]
C. Eigenvalues 2 and 3; eigenvectors [1,1] D. Eigenvalues 6 and 1; eigenvectors along
and [1,-1] coordinate axes
Correct: A - Eigenvalues 2 and 3; eigenvectors along coordinate axes
Rationale:For a diagonal matrix, eigenvalues are the diagonal entries (2 and 3) and
eigenvectors are the standard basis vectors e1 and e2. Off-diagonal zeros mean no rotation
of eigenbasis, so eigenvectors lie along coordinate axes.
Why the other answers are wrong:
B. The eigenvalues of a diagonal matrix are its diagonal entries, not 5 and 1.
C. Eigenvectors [1,1] and [1,-1] correspond to a different matrix (e.g., [[4,2],[2,4]]).
Page 3
, Section A - Introduction TO Artificial Intelligence
D. Eigenvalues are not products of diagonal entries; 6 is incorrect.
Reference: Strang, G. (2023). Introduction to Linear Algebra, 6th Ed., Ch. 6.
Q3.
In NumPy, what is the output shape of `np.arange(12).reshape(3,4)[:, 1:3].sum(axis=0)`?
A. Scalar B. Shape (2,)
C. Shape (3,) D. Shape (3,2)
Correct: B - Shape (2,)
Rationale:Slicing `[:, 1:3]` yields a (3,2) array; summing along axis=0 collapses rows,
producing a shape (2,) vector. Axis=0 sums over rows, leaving columns.
Why the other answers are wrong:
A. A scalar results only if summing over all axes or using .sum() without axis.
C. Shape (3,) would result from summing axis=1, not axis=0.
D. Shape (3,2) is the pre-sum slice shape, not post-reduction.
Reference: McKinney, W. (2022). Python for Data Analysis, 3rd Ed., Ch. 4 (NumPy Basics).
Q4.
A spam filter trained on 10,000 labeled emails achieves 99% training accuracy but 72% test
accuracy. Which remedy is MOST appropriate?
A. Increase model complexity with more B. Apply regularization and gather more
hidden layers training data
C. Reduce the test set size to lower D. Switch from supervised to unsupervised
variance learning
Correct: B - Apply regularization and gather more training data
Rationale:The large train-test gap signals overfitting; regularization (L1/L2, dropout) and
more data reduce variance. Increasing complexity worsens overfitting, and switching
paradigms is unwarranted when labels exist.
Why the other answers are wrong:
A. More complexity increases overfitting, widening the train-test gap.
C. Shrinking the test set reduces evaluation reliability, not model generalization.
D. Unsupervised learning discards label information and is inappropriate for spam
classification.
Reference: Géron, A. (2022). Hands-On Machine Learning, 3rd Ed., Ch. 4.
Page 4
