CSE327 AI Notes

CSE327 AI Notes - Ch. 1 Introduction o Rationality Ideal...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Ch. 1 – Introduction o Rationality Ideal concept of intelligence System is rational if it does the right thing given what it knows o definitions of “artificial intelligence” think like humans machines with minds act like humans make computers do things at which people are better. think and act rationally. Study of computations that make it possible to perceive reason and act. o The Turing Test Designed to provide operational definition of intelligence. The computer passes the test if a human, after posing written questions, cannot tell that the responses are coming from a computer instead of a person. Ch. 2 - Agents o PEAS descriptions performance measure, environment, actuators, sensors Credit card agent: o High number of detections, env=credit transactions, act=alert system, sensors=receive transactions DB Fingerprint matcher: o P=number correct matches. Env = db of fingerprints, input image…actuators=API for DB search, result output mechanism… sensors=input image, images from DB. o properties of task environments fully observable vs. partially observable, deterministic vs. stochastic vs, strategic, episodic vs. sequential, static vs. dynamic, discrete vs. continuous, single agent vs. multiagent Observables o If sensors give agent access to complete state of the environment, at each point in time, then we say the task is fully observable. Must detect all relevant aspects of the state. Fully=better – agent need not maintain internal state to track the world. Deterministic vs. stochastic
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
o If the next state is determined by the current state + action, then environment is deterministic, otherwise stochastic. Episodic vs. Sequential o In an episodic environment, experience is divided into atomic episodes that consist of a perception then an action, with the next episode NOT DEPENDENT on the action taken. Static vs. Dynamic o If environment can change while agent is deciding on action, then it is dynamic. Discrete vs. continuous
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 6

CSE327 AI Notes - Ch. 1 Introduction o Rationality Ideal...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online