INTRODUCTION TO AI FOR COMPUTER
SCIENTISTS EXAM PREPARATION TEST
BANK WITH CORRECT ANSWERS
●● General Artificial Intelligence GA I
Answer: General Artificial Intelligence GA I also known as Strong AI is
a theoretical form of AI capable of performing any intellectual task a
human can across multiple domains with full adaptability reasoning and
contextual awareness not currently achieved and often used in exam
scenarios to contrast with task specific systems example: a single system
diagnosing disease writing software and driving autonomously without
retraining
●● Narrow Artificial Intelligence NA I
Answer: Narrow Artificial Intelligence NA I also called Weak AI refers
to systems designed for a specific task operating within predefined
constraints without true understanding or consciousness this represents
nearly all current AI implementations example: a fraud detection model
identifying suspicious credit card transactions based on learned patterns
●● Turing Test
Answer: Turing Test is a benchmark for evaluating machine intelligence
where a human evaluator interacts with both a machine and a human and
if the evaluator cannot reliably distinguish between them the machine is
,considered to exhibit human like intelligence often referenced in
discussions of conversational AI
●● Machine Learning ML
Answer: Machine Learning ML is a subset of Artificial Intelligence AI
that enables systems to learn patterns from data and improve
performance over time without explicit programming widely used in
cybersecurity for anomaly detection spam filtering and predictive
analytics example: an email system learning to classify spam based on
user behavior and message features
●● Training Data
Answer: Training Data is the dataset used to train machine learning
models allowing them to identify patterns and relationships the quality
representativeness and bias of this data directly impact model
performance and fairness example: labeled network traffic data used to
train an intrusion detection model
●● Supervised Learning
Answer: Supervised Learning is a machine learning approach where
models are trained on labeled input output pairs to learn mappings used
for classification and regression tasks and commonly tested in scenarios
involving prediction with known outcomes example: predicting whether
a file is malware based on labeled training data
●● Unsupervised Learning
, Answer: Unsupervised Learning is a machine learning method that
identifies patterns structures or groupings in unlabeled data often used
for clustering anomaly detection and behavioral analysis in
cybersecurity example: clustering user activity to detect abnormal login
behavior
●● Model
Answer: Model is a mathematical representation produced by a machine
learning algorithm that maps inputs to outputs enabling prediction
classification or decision making used during both training and inference
phases example: a trained neural network classifying network packets as
benign or malicious
●● Spam Filter
Answer: Spam Filter is a machine learning application that classifies
emails as spam or legitimate using features such as keywords sender
reputation and message structure improving over time with feedback
example: filtering phishing emails before they reach user inboxes
●● Pattern Recognition
Answer: Pattern Recognition is the capability of AI systems to identify
regularities correlations and structures within data foundational to tasks
such as image recognition anomaly detection and fraud detection
example: detecting unusual login patterns indicating a possible account
takeover
SCIENTISTS EXAM PREPARATION TEST
BANK WITH CORRECT ANSWERS
●● General Artificial Intelligence GA I
Answer: General Artificial Intelligence GA I also known as Strong AI is
a theoretical form of AI capable of performing any intellectual task a
human can across multiple domains with full adaptability reasoning and
contextual awareness not currently achieved and often used in exam
scenarios to contrast with task specific systems example: a single system
diagnosing disease writing software and driving autonomously without
retraining
●● Narrow Artificial Intelligence NA I
Answer: Narrow Artificial Intelligence NA I also called Weak AI refers
to systems designed for a specific task operating within predefined
constraints without true understanding or consciousness this represents
nearly all current AI implementations example: a fraud detection model
identifying suspicious credit card transactions based on learned patterns
●● Turing Test
Answer: Turing Test is a benchmark for evaluating machine intelligence
where a human evaluator interacts with both a machine and a human and
if the evaluator cannot reliably distinguish between them the machine is
,considered to exhibit human like intelligence often referenced in
discussions of conversational AI
●● Machine Learning ML
Answer: Machine Learning ML is a subset of Artificial Intelligence AI
that enables systems to learn patterns from data and improve
performance over time without explicit programming widely used in
cybersecurity for anomaly detection spam filtering and predictive
analytics example: an email system learning to classify spam based on
user behavior and message features
●● Training Data
Answer: Training Data is the dataset used to train machine learning
models allowing them to identify patterns and relationships the quality
representativeness and bias of this data directly impact model
performance and fairness example: labeled network traffic data used to
train an intrusion detection model
●● Supervised Learning
Answer: Supervised Learning is a machine learning approach where
models are trained on labeled input output pairs to learn mappings used
for classification and regression tasks and commonly tested in scenarios
involving prediction with known outcomes example: predicting whether
a file is malware based on labeled training data
●● Unsupervised Learning
, Answer: Unsupervised Learning is a machine learning method that
identifies patterns structures or groupings in unlabeled data often used
for clustering anomaly detection and behavioral analysis in
cybersecurity example: clustering user activity to detect abnormal login
behavior
●● Model
Answer: Model is a mathematical representation produced by a machine
learning algorithm that maps inputs to outputs enabling prediction
classification or decision making used during both training and inference
phases example: a trained neural network classifying network packets as
benign or malicious
●● Spam Filter
Answer: Spam Filter is a machine learning application that classifies
emails as spam or legitimate using features such as keywords sender
reputation and message structure improving over time with feedback
example: filtering phishing emails before they reach user inboxes
●● Pattern Recognition
Answer: Pattern Recognition is the capability of AI systems to identify
regularities correlations and structures within data foundational to tasks
such as image recognition anomaly detection and fraud detection
example: detecting unusual login patterns indicating a possible account
takeover
