Artificial Intelligence Flashcards
7 cards from real Artificial Intelligence practice questions. Tap to flip, then mark Knew It or Still Learning — missed cards come back until you master them.
Read the first 7 Artificial Intelligence flashcards as text
Which technique adapts a large pre-trained model to a specific task using a smaller labeled dataset?
Answer: Fine-tuning
Fine-tuning continues training a pre-trained model on task-specific data, leveraging transfer learning.
An AI chatbot confidently states a false fact that sounds plausible. What is this phenomenon called?
Answer: Hallucination
Hallucination refers to language models generating fluent but factually incorrect or fabricated content.
In a Markov decision process, what property must state transitions satisfy?
Answer: They depend only on the current state and action
The Markov property requires that the next state depends only on the current state and action, not past history.
Which evaluation approach splits data into multiple folds, training and testing on different combinations?
Answer: Cross-validation
K-fold cross-validation rotates which fold is held out for testing, giving a more reliable performance estimate.
A recommendation system suggests movies based on what similar users enjoyed. What is this approach called?
Answer: Collaborative filtering
Collaborative filtering recommends items using the preferences of users with similar tastes.
What is the main advantage of using word embeddings over one-hot encoding in NLP?
Answer: They capture semantic similarity between words in dense vectors
Embeddings place semantically similar words close together in vector space, unlike sparse one-hot vectors.
Which concern is central to explainable AI (XAI)?
Answer: Making model decisions understandable to humans
XAI aims to make black-box model decisions transparent and interpretable, which is critical in high-stakes domains.