Jimma University,JiT Depatment of Computing Introduction To Artificial Intelligence Zelalem H.

Outline (1)Introduction (2) Intelligent Agents What is AI? Foundations of AI State of the art in AI History of AI (Reading assignment) (2) Intelligent Agents Agents and environments Rationality The Nature of environments The structure of agents

1. Introduction For thousands of years, we have tried to understand how we think! AI, goes further still; it attempts not just to understand but also to build intelligent entities.

Introduction… What is AI? Some possible definitions Thinking humanly Thinking rationally Acting humanly Acting rationally

Introduction… Thinking humanly Cognitive science: the brain as an information processing machine Requires scientific theories of how the brain works How to understand cognition as a computational process? Introspection: try to think about how we think Predict and test behavior of human subjects Image the brain, examine neurological data

Introduction… Acting humanly The Turing Test What capabilities would a computer need to have to pass the Turing Test? Natural language processing Knowledge representation Automated reasoning Machine learning

Introduction… Turing Test: Criticism What are some potential problems with the Turing Test? Some human behavior is not intelligent Some intelligent behavior may not be human Human observers may be easy to fool Chinese room argument: one may simulate intelligence without having true intelligence Is passing the Turing test a good scientific goal?

Introduction… Thinking rationally Idealized or “right” way of thinking Logic: patterns of argument that always yield correct conclusions when supplied with correct premises “Socrates is a man; All men are mortal; Therefore Socrates is mortal.” Beginning with Aristotle, philosophers and mathematicians have attempted to formalize the rules of logical thought

Introduction… Thinking rationally … Logicist approach to AI: describe problem in formal logical notation and apply general deduction procedures to solve it Problems with the logicist approach Computational complexity of finding the solution Describing real-world problems and knowledge in logical notation A lot of intelligent or “rational” behavior has nothing to do with logic

Introduction… Acting rationally A rational agent is one that acts to achieve the best outcome Goals are application-dependent and are expressed in terms of the utility of outcomes Being rational means maximizing your expected utility This definition of rationality only concerns the decisions/actions that are made, not the cognitive process behind them

Introduction… Acting rationally… Any disadvantages? Advantages Generality: goes beyond explicit reasoning, and even human cognition altogether Practicality: can be adapted to many real-world problems Amenable to good scientific and engineering methodology Avoids philosophy and psychology Any disadvantages? Not feasible in complicated envt’s Computational demands are just too high

AI Foundations Philosophy Mathematics Can formal rules be used to draw valid conclusions? How does the mind arise from a physical brain? Where does knowledge come from? How does knowledge lead to action? Mathematics What are the formal rules to draw valid conclusions? What can be computed? How do we reason with uncertain information?

AI Foundations… Economics Neuroscience Psychology How should we make decisions so as to maximize payoff? How should we do this when others may not go along? Neuroscience How do brains process information? Psychology How do humans and animals think and act?

AI Foundations… Computer Engineering How can we build an efficient computer? Control Theory and Cybernetics How can artifacts operate under their own control? Linguistics How does language relate to thought?

The state-of-the-art Robotic Vehicles Speech recognition Autonomous planning and scheduling Game playing Spam fighting, fraud detection Robotics Machine translation Vision

The History of Artificial intelligence Reading Assignment From Page 16 to 28 Russell and Norvig, 3rd edition

2. Intelligent Agents An agent is anything that can be viewed as perceiving its environment through sensors and acting upon that environment through actuators

Agent function The agent function maps from percept histories to actions The agent program runs on the physical architecture to produce the agent function agent = architecture + program

Vacuum-cleaner world Percepts: Location and status, e.g., [A,Dirty] Actions: Left, Right, Suck, NoOp function Vacuum-Agent([location,status]) returns an action if status = Dirty then return Suck else if location = A then return Right else if location = B then return Left

Rational agents For each possible percept sequence, a rational agent should select an action that is expected to maximize its performance measure, given the evidence provided by the percept sequence and the agent’s built-in knowledge Performance measure An objective criterion for success of an agent's behavior

What does rationality mean? Rationality is not omniscience Percepts may not supply all the relevant information Consequences of actions may be unpredictable An agent is autonomous if its behavior is determined by its own experience (with ability to learn and adapt)

Specifying the task environment Problem specification: Performance measure, Environment, Actuators, Sensors (PEAS) Example: automated taxi driver Performance measure Safe, fast, legal, comfortable trip, maximize profits Environment Roads, other traffic, pedestrians, customers Actuators Steering wheel, accelerator, brake, signal, horn Sensors Cameras, sonar, speedometer, GPS, odometer, engine sensors, keyboard

Agent: Part-sorting robot Performance measure Percentage of parts in correct bins Environment Conveyor belt with parts, bins Actuators Robotic arm Sensors Camera, joint angle sensors

Agent: Spam filter Performance measure Environment Actuators Sensors Minimizing false positives, false negatives Environment A user’s email account Actuators Mark as spam, delete, etc. Sensors Incoming messages, other information about user’s account

Environment types Fully observable (vs. partially observable): The agent's sensors give it access to the complete state of the environment at each point in time Deterministic (vs. stochastic): The next state of the environment is completely determined by the current state and the agent’s action Episodic (vs. sequential): The agent's experience is divided into atomic “episodes,” and the choice of action in each episode depends only on the episode itself

Environment types Static (vs. dynamic): Discrete (vs. continuous): The environment is unchanged while an agent is deliberating Semidynamic: the environment does not change with the passage of time, but the agent's performance score does Discrete (vs. continuous): The environment provides a fixed number of distinct percepts, actions, and environment states Time can also evolve in a discrete or continuous fashion

Environment types Single agent (vs. multi-agent): An agent operating by itself in an environment Known (vs. unknown): The agent knows the rules of the environment

Examples Fully observable Deterministic Episodic Static Discrete Chess w Clock without clock Taxi Fully observable Deterministic Episodic Static Discrete Single Agent Yes Yes No Strategic No Strategic No No No Semi Yes No Yes Yes No No No No

Hierarchy of agent types Simple reflex agents Model-based reflex agents Goal-based agents Utility-based agents

Simple reflex agent Select action on the basis of current percept, ignoring all past percepts

Model-based reflex agent Maintains internal state that keeps track of aspects of the environment that cannot be currently observed

Goal-based agent The agent uses goal information to select between possible actions in the current state

Utility-based agent The agent uses a utility function to evaluate the desirability of states that could result from each possible action

A learning agent to build learning machines and then to teach them.

learning element, which is responsible for making improvements, A learning Agent learning element, which is responsible for making improvements, performance element, which is responsible for selecting external actions. The learning element uses feedback from the critic on how the agent is doing and determines how the performance element should be modified to do better in the future. problem generator: responsible for suggesting actions that will lead to new and informative experiences

Questions?