5.1.2 Understanding artificial intelligence (AI):

• What does the acronym AI stand for?

  Artificial Intelligence
• Machines improve performance through experience and data analysis in AI.


  True
• What is another name for Narrow AI?

  Weak AI
• Supervised learning requires labeled data for training.


  True
• What are the key characteristics of AI?

  Learning, reasoning, perception
• Order the types of AI from least to most advanced:

  1️⃣ Narrow AI

  2️⃣ General AI

  3️⃣ Artificial Superintelligence
• Deep learning models require manual feature engineering.

  False
• AI refers to the ability of a machine to perform tasks that typically require human intelligence
• Match the type of AI with its definition:

  Narrow AI ↔️ Designed for specific tasks

  General AI ↔️ Broad capabilities like human intelligence

  Artificial Superintelligence ↔️ Surpasses human intelligence
• Machine learning is a subset of AI
• Match the type of machine learning with its example:

  Supervised Learning ↔️ Spam detection

  Unsupervised Learning ↔️ Customer segmentation

  Reinforcement Learning ↔️ Game-playing algorithms
• Machines use perception to interpret sensory data.


  True
• Deep learning uses artificial neural networks
• What is deep learning a subset of?

  Machine learning
• Deep learning models require manual feature engineering.

  False
• Deep learning models use highly complex, multi-layered neural networks
• AI has applications only in robotics and automation.

  False
• What is an example of AI use in healthcare for disease detection?

  Medical imaging analysis
• Predictive analytics can identify fraudulent transactions.

  True
• AI is the ability of machines to perform tasks requiring human intelligence
• What is another name for narrow AI?

  Weak AI
• How does artificial superintelligence compare to narrow AI in terms of capabilities?

  Superintelligence exceeds human limits
• Match the type of machine learning with its definition:

  Supervised Learning ↔️ Trained on labeled data

  Unsupervised Learning ↔️ Discover patterns from unlabeled data

  Reinforcement Learning ↔️ Learns by interacting with an environment
• Supervised learning uses labeled data to predict outputs for new, unseen inputs.


  True
• What is the primary difference between deep learning and traditional machine learning in terms of feature engineering?

  Deep learning automates feature extraction
• Deep learning models use highly complex, multi-layered neural networks
• Match the AI application area with its description:

  Healthcare ↔️ Disease diagnosis and treatment

  Robotics and Automation ↔️ Autonomous systems and tasks

  Natural Language Processing ↔️ Understanding and generating language

  Computer Vision ↔️ Processing images and videos
• Predictive analytics uses AI to forecast future trends and outcomes.


  True
• Deep learning models use artificial neural networks to learn from data
• What is a key difference between deep learning and traditional machine learning in terms of feature engineering?

  Deep learning is automatic
• What is an example task where deep learning excels without explicit programming of visual features?

  Image recognition
• Match the AI application area with its description:

  Healthcare ↔️ AI systems assist with diagnosis

  Robotics and Automation ↔️ Enables robots to perceive and act

  Natural Language Processing ↔️ Processes human language

  Computer Vision ↔️ Identifies and processes images

  Predictive Analytics ↔️ Forecasts trends based on data
• Virtual assistants like Alexa use natural language processing
• What are the four key capabilities of AI mentioned in the text?

  Learning, reasoning, problem-solving, perception
• AI systems improve performance through experience and data analysis.


  True
• Narrow AI is designed to perform a specific task
• General AI currently exists and matches human-level intelligence.

  False
• Machine learning is a subset of artificial intelligence
• Machine learning is a subset of artificial intelligence that enables systems to learn and improve from experience without being explicitly programmed
• Match the type of machine learning with its definition:

  Supervised Learning ↔️ Trained on labeled data

  Unsupervised Learning ↔️ Discovers patterns in unlabeled data

  Reinforcement Learning ↔️ Learns by interacting with feedback