INTRODUÇÃO AOS SISTEMAS INTELIGENTES Prof. Dr. Celso A.A. Kaestner PPGEE-CP / UTFPR Agosto de 2011.

Apresentação em tema: "INTRODUÇÃO AOS SISTEMAS INTELIGENTES Prof. Dr. Celso A.A. Kaestner PPGEE-CP / UTFPR Agosto de 2011."— Transcrição da apresentação:

1 INTRODUÇÃO AOS SISTEMAS INTELIGENTES Prof. Dr. Celso A.A. Kaestner PPGEE-CP / UTFPR Agosto de 2011

2 Referências Stuart Russel e Peter Norvig, Artificial Intelligence, a Modern Approach: http://aima.cs.berkeley.edu http://aima.cs.berkeley.edu Outras referências indicadas na proposta da disciplina.

3 INTRODUÇÃO

4 O que é IA ?

5 O teste de Turing

6 O que é IA ? Abordagens: – Simbólica:utiliza formalismos do tipo lógico para simular o comportamento inteligente expresso através da linguagem. Base para os sistemas especialistas. – Conexionista: visa à modelagem da inteligência humana através da simulação dos componentes do cérebro, isto é, de seus neurônios, e de suas interligações. Base para as Redes Neurais. – Evolutiva: simula a evolução natural para encontrar soluções para problemas complexos. Base para métodos de otimização, como os Algoritmos Genéticos. História da IA, linha do tempo: http://en.wikipedia.org/wiki/Artificial_intelligence http://en.wikipedia.org/wiki/Artificial_intelligence

7 Pré-história da IA PhilosophyLogic, methods of reasoning, mind as physical system foundations of learning, language, rationality MathematicsFormal representation and proof algorithms, computation, (un)decidability, (in)tractability, probability Economicsutility, decision theory Neurosciencephysical substrate for mental activity Psychology phenomena of perception and motor control, experimental techniques Computer building fast computers engineering Control theorydesign systems that maximize an objective function over time Linguisticsknowledge representation, grammar

8 Resumo da História da IA 1943 McCulloch & Pitts: Boolean circuit model of brain 1950 Turing's "Computing Machinery and Intelligence" 1956Dartmouth meeting: "Artificial Intelligence" adopted 195269Look, Ma, no hands! 1950sEarly AI programs, including Samuel's checkers program, Newell & Simon's Logic Theorist, Gelernter's Geometry Engine 1965Robinson's complete algorithm for logical reasoning 196673AI discovers computational complexity Neural network research almost disappears 196979Early development of knowledge-based systems 1980-- AI becomes an industry 1986-- Neural networks return to popularity 1987--AI becomes a science 1995--The emergence of intelligent agents

9 Estado da arte Deep Blue defeated the reigning world chess champion Garry Kasparov in 1997 Proved a mathematical conjecture (Robbins conjecture) unsolved for decades No hands across America (driving autonomously 98% of the time from Pittsburgh to San Diego) During the 1991 Gulf War, US forces deployed an AI logistics planning and scheduling program that involved up to 50,000 vehicles, cargo, and people NASA's on-board autonomous planning program controlled the scheduling of operations for a spacecraft Proverb solves crossword puzzles better than most humans

10 Agentes e ambientes

11

12 Agente racional 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 whatever built-in knowledge the agent has.

13 Agentes e ambientes

14 Tipos de agentes Simple reflex agents Model-based reflex agents Goal-based agents Utility-based agents

15 Agente reflexo simples

16 Agente reflexo baseado em modelos

17 Agente dirigido por objetivos

18 Agente baseado em utilidade

19 PEAS PEAS: Performance measure, Environment, Actuators, Sensors Design of an 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

20 PEAS Agent: Medical diagnosis system Performance measure: Healthy patient, minimize costs, lawsuits Environment: Patient, hospital, staff Actuators: Screen display (questions, tests, diagnoses, treatments, referrals) Sensors: Keyboard (entry of symptoms, findings, patient's answers)

21 Diferentes ambientes Fully observable (vs. partially observable): An 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 action executed by the agent. (If the environment is deterministic except for the actions of other agents, then the environment is strategic) Episodic (vs. sequential): The agent's experience is divided into atomic "episodes" (each episode consists of the agent perceiving and then performing a single action), and the choice of action in each episode depends only on the episode itself.

22 Diferentes agentes, diferentes ambientes Static (vs. dynamic): The environment is unchanged while an agent is deliberating. (The environment is semidynamic if the environment itself does not change with the passage of time but the agent's performance score does) Discrete (vs. continuous): A limited number of distinct, clearly defined percepts and actions. Single agent (vs. multiagent): An agent operating by itself in an environment.