KECERDASAN BUATAN Artificial intelligence

1
KECERDASAN BUATAN( Artificial intelligence )

• Disusun oleh
• Ervien Siska Aprithama
• Ari handoko
• Risco ridho
• Wahyudi
• Sopy
• Sigit

2
What is AI?

• A science of making intelligent machines
• A study to make computer systems to have
  intelligence

3
Goals of AI

• Replicate human intelligence
• Solve knowledge-intensive tasks
• Intelligent connection of perception and action
• Enhance human-human, human-computer and
  computer-computer interaction /communication

4
Some Application Areas of AI

• Game Playing
• Speech Recognition
• Computer Vision
• Expert Systems
• Diagnostic Systems
• System Configuration
• Financial Decision Making
• Classification Systems

5
Some Application Areas of AI

• Mathematical Theorem Proving
• Natural Language Understanding
• Scheduling and Planning

6
Some AI "Grand Challenge Problems

• Translating telephone
• Accident-avoiding car
• Aids for the disabled
• Smart clothes
• Intelligent agents that monitor and manage
  information by filtering, digesting, abstracting
• Tutors
• Self-organizing systems, e.g., that learn to
  assemble something by observing a human do it.

7
A Framework for Building AI Systems

• Perception
• Reasoning
• Action

8
Some Fundamental Issues for Most AI Problems

• Representation
• Search
• Inference
• Learning
• Planning

9
Design Methodology and Goals

• Engineering Goal
• Science Goal
• Alternatives methodology
• Think like humans"cognitive science, Ex. GPS 2
• Think rationally, formalize inference process
  "laws of thought"
• Act like humans Ex. ELIZA, Turing Test 4
• Act rationally "satisficing" methods

10
Symbols versus Signals

• Physical-Symbol System information processing
  model

11
Intelligent Agents

• What is an Intelligent Agent?
• Agent Characteristics
• Situatedness
• Autonomy
• Adaptivity
• Sociability

12
sensor
percepts
environment
agent
actions
effectors
13
Examples of Agents
14
A Skeleton Agent
function SKELETON-AGENT(percept) returns
action static memory, the agents memory of the
world memory UPDATE-MEMORY(memory,percep
t) action CHOOSE-BEST-ACTION(memory) m
emory UPDATE-MEMORY(memory,action) retur
n action
15
How to Evaluate an Agent's Behavior/Performance?

• Rationality
• the percept sequence
• its built-in and acquired knowledge
• Types of objective performance measures
• false alarm rate
• false dismissal rate
• time taken
• resources required
• effect on environment, etc.

16
Approaches to Agent Design

• Simple Reflex Agent
• Table lookup of percept-action pairs defining all
  possible condition-action rules necessary to
  interact in an environment
• Problems
• Too big to generate and to store (Chess has about
  10120 states, for example)
• No knowledge of non-perceptual parts of the
  current state
• Not adaptive to changes in the environment
  requires entire table to be updated if changes
  occur
• Looping Can't make actions conditional

17

• Reflex Agent with Internal State
• Encode "internal state" of the world
• Needed because sensors do not usually give the
  entire state of the world
• Requires ability to represent change in the world
• Example Rodney Brooks's Subsumption Architecture
• Goal-Based Agent
• Choose actions so as to achieve a goal
• Need to add goals to decide which situations are
  good
• Deliberative instead of reactive
• Involves consideration of the future

18

• Utility-Based Agent
• How to decide which one is best?
• A goal specifies a crude distinction between a
  happy and unhappy state
• Utility function U State -- Realsindicating a
  measure of success or happiness when at a given
  state
• Allows decisions comparing choice between
  conflicting goals, and choice between likelihood
  of success and importance of goal (if achievement
  is uncertain)

19
Properties of Environment

• Accessible vs. inaccessible
• Deterministic vs. nondeterministic
• Episodic vs. nonepisodic
• Static vs. dynamic
• Descrete vs. continuous

20
Summary Chap.2

• An agent is something that perceives and acts in
  an environment
• An ideal agent is one that always takes the
  action that is expected to maximize its
  performance measure, given the percept sequence
  it has seen so far
• An agent is autonomous to the extent that its
  action choices depend on its own experience,
  rather than on knowledge of the environment that
  has been built-in by the designer
• An agent program maps from percept to an action,
  while updating internal state
• There exists a variety of basic agent program
  designs, depending on the kind of information
  made explicit and used in the decision process
• Reflex agents respond immediately to percepts,
  goal-based agents act so that they will achieve
  their goals, and utility-based agents try to
  maximize their own happiness
• The process of making decisions by reasoning with
  knowledge is central to AI and to successful
  agent design
• Some environments are more demanding than others

21
PERNAHKAH anda membayangkan dapat berbicara
dengan seseorang yang telah meninggal 5 tahun
lalu? Jangan keburu membayangkan bahwa anda harus
mendatangi seorang arwah.
Care-O-bot II, robot pembantu bagi penyandang
cacat
22
(No Transcript)
23
(No Transcript)