AI Study Guide 2026
Everything you need to pass the AI exam in one place: the exam format, every topic to study, real practice questions with explanations, flashcards, and full-length practice tests. Free, no sign-up needed.
📋 AI Exam Format at a Glance
📚 AI Topics to Study (21)
✍️ Sample AI Questions & Answers
1. What is 'shadow mode' deployment in MLOps?
Shadow mode runs a new model on real traffic in parallel with the live model, comparing outputs without impacting users.
2. Which of the following uses artificial intelligence?
Artificial intelligence is extensively applied in areas requiring the understanding and processing of human language, such as text analytics and Natural Language Processing (NLP). These AI capabilities enable machines to interpret, analyze, and generate human language, facilitating applications like chatbots, sentiment analysis, machine translation, and information extraction.
3. Which technique is used to visualize which parts of an input image most influence a CNN's classification decision?
Grad-CAM uses gradients flowing into the final convolutional layer to produce a heatmap highlighting the regions most important to the prediction.
4. In the context of decision trees, what is information gain?
Information gain measures how much a feature split reduces entropy (disorder) in the target variable — features with the highest information gain are chosen as split points to build a tree that separates classes most effectively.
5. Which trait is frequently connected to artificial intelligence? (a) Consciousness and emotion
Current artificial intelligence systems are primarily examples of 'narrow AI,' meaning they are designed to perform specific tasks within limited domains. Unlike human general intelligence, they lack consciousness, emotion, or the ability to apply knowledge broadly across different contexts. Their intelligence is specialized and confined to their training data and programmed objectives.
6. What is the purpose of 'model quantization' in the context of ML deployment?
Quantization converts model weights from 32-bit floats to 8-bit integers, shrinking memory footprint and speeding up inference with minimal accuracy loss.