Artificial Intelligence Artificial Intelligence 2 — Questions and Answers
Question 1: Which search algorithm is guaranteed to find the optimal solution when using an admissible heuristic?
- Depth-first search
- A* search (Correct answer)
- Hill climbing
- Greedy best-first search
Correct answer: A* search
A* search is optimal when its heuristic never overestimates the true cost to the goal.
Question 2: In machine learning, what problem occurs when a model performs well on training data but poorly on unseen data?
- Underfitting
- Data leakage
- Overfitting (Correct answer)
- Vanishing gradients
Correct answer: Overfitting
Overfitting means the model memorized training-specific noise instead of learning generalizable patterns.
Question 3: Which component of an expert system contains the domain-specific facts and rules?
- Inference engine
- User interface
- Explanation module
- Knowledge base (Correct answer)
Correct answer: Knowledge base
The knowledge base stores the facts and if-then rules that the inference engine reasons over.
Question 4: What does the activation function in a neural network primarily provide?
- Non-linearity (Correct answer)
- Faster training speed
- Weight initialization
- Data normalization
Correct answer: Non-linearity
Activation functions like ReLU introduce non-linearity, letting networks model complex relationships.
Question 5: In reinforcement learning, what does the agent receive from the environment after taking an action?
- A labeled dataset
- A gradient update
- A decision tree
- A reward signal and new state (Correct answer)
Correct answer: A reward signal and new state
The environment returns a reward and the next state, which the agent uses to improve its policy.
Question 6: Which of the following is an example of unsupervised learning?
- Spam email classification
- Customer clustering by purchase behavior (Correct answer)
- House price prediction
- Handwritten digit recognition with labels
Correct answer: Customer clustering by purchase behavior
Clustering groups unlabeled data by similarity, requiring no predefined output labels.
Question 7: The Turing Test is designed to evaluate what aspect of a machine?
- Its computational speed
- Its memory capacity
- Its ability to exhibit human-indistinguishable conversation (Correct answer)
- Its ability to solve math proofs
Correct answer: Its ability to exhibit human-indistinguishable conversation
Alan Turing proposed the test to judge whether a machine's conversational responses are indistinguishable from a human's.
Which search algorithm is guaranteed to find the optimal solution when using an admissible heuristic?