Week 1: Intro to AI & Rational Agents Flashcards
What is Artificial Intelligence?
Artificial Intelligence (AI) is the study of how to make computers or machines perform tasks that require human-like intelligence, such as learning, reasoning, and problem-solving.
What are the four main approaches to defining AI?
- Thinking humanly, 2. Thinking rationally, 3. Acting humanly, 4. Acting rationally.
What is the Turing Test used for?
The Turing Test assesses a machine’s ability to exhibit intelligent behavior indistinguishable from a human.
What does ‘acting rationally’ mean in AI?
It means choosing actions that maximize goal achievement based on current knowledge and percepts.
What is an intelligent agent?
An intelligent agent perceives its environment and takes actions to achieve its goals rationally.
What are the components of an agent?
Sensors (to perceive), actuators (to act), agent program (to decide actions), and agent function (the mapping from percepts to actions).
What is a rational agent?
A rational agent selects actions expected to maximize its performance measure based on its percept sequence and knowledge.
What is the difference between an agent program and an agent function?
The agent function is a theoretical mapping from percepts to actions; the agent program is the actual implementation of this behavior.
What is a performance measure in AI?
It is a metric that evaluates how well an agent achieves its goals in an environment.
What does ‘PEAS’ stand for in task environments?
Performance measure, Environment, Actuators, Sensors.
What is meant by ‘bounded rationality’?
It refers to making the best possible decision given limited time and resources.
What are some examples of AI in real life?
Examples include autonomous cars, voice assistants, recommendation systems, and facial recognition.
What is the ‘vacuum cleaner world’ used to illustrate?
It is a simplified environment used to teach how agents make decisions based on percepts and rationality.
What is an example of irrational agent behavior in the vacuum cleaner world?
Continuing to move after all dirt is cleaned, wasting energy unnecessarily.
What does it mean for an agent to have autonomy?
An autonomous agent learns and adapts using its own percepts rather than relying entirely on pre-programmed knowledge.
What’s the difference between strong AI and weak AI?
Strong AI refers to machines with consciousness; weak AI performs tasks without genuine understanding or awareness.
What is the history milestone marked by the Dartmouth Conference in 1956?
It was the founding event of the field of Artificial Intelligence as a formal academic discipline.
What caused the first ‘AI winter’?
Disillusionment with progress and overpromising led to funding cuts and skepticism about AI.
What marked the second golden age of AI?
Breakthroughs in machine learning, deep learning, and successes like AlphaGo, IBM Watson, and self-driving cars.
What are the two dimensions used to categorize AI definitions?
- Thinking vs. Acting, 2. Human-likeness vs. Rationality.
What does it mean for a system to act rationally but not think?
It chooses the best action without necessarily replicating human thought processes—like reflexive agents.
What is a reflex agent?
An agent that selects actions based on current percepts only, without considering history or planning.
Why is rationality more scientific than human-likeness in AI?
Because rationality can be mathematically defined and evaluated independently of subjective human behavior.
What does ‘machine learning’ enable in AI?
It allows systems to adapt to new data and improve performance without being explicitly programmed for every scenario.
