artificial intelligence a brief introduction
DESCRIPTION
aslab . org. Artificial Intelligence A Brief Introduction. Ricardo Sanz. May 20, 2004. autonomous systems laboratory. Contents. Basic Ideas History Technology Robots Agents. Core Ideas. What is AI ?. What is AI?. Acting humanly : The Turing test (1950) - PowerPoint PPT PresentationTRANSCRIPT
aslab 12004/03/24Sanz / Artificial Intelligence: An Introduction
aslab.org
May 20, 2004
Artificial IntelligenceA Brief Introduction
Ricardo Sanz
autonomous systems laboratory
2004/03/24Sanz / Artificial Intelligence: An Introduction 2aslab
ContentsContents
Basic Ideas History Technology Robots Agents
aslab 32004/03/24Sanz / Artificial Intelligence: An Introduction
Core Ideas
What is AI ?
2004/03/24Sanz / Artificial Intelligence: An Introduction 4aslab
What is AI?What is AI?
Acting humanly: The Turing test (1950) What do we need to pass the test
Thinking humanly: Cognitive modeling “Think-aloud” to learn from human and recreate in computer
programs (GPS)
Thinking rationally: Syllogisms, Logic Acting rationally: A rational agent
2004/03/24Sanz / Artificial Intelligence: An Introduction 5aslab
Foundations of AIFoundations of AI
Philosophy (428 B.C. - Present) – reasoning and learning Can formal rules be used to draw valid conclusions? How does the mental I arise from a physical brain? Where does knowledge come from? How does knowledge lead to action?
2004/03/24Sanz / Artificial Intelligence: An Introduction 6aslab
Foundations of AIFoundations of AI
Mathematics (c. 800 - Present) - logic, probability, decision making, computation What are the formal rules to draw conclusions? What can be computed? How do we reason with uncertain information?
Economics (1776-present) How should we make decisions so as to maximize payoff? How should we do this when others may not go along? How should we do this when the payoff may be far in the
future?
2004/03/24Sanz / Artificial Intelligence: An Introduction 7aslab
Foundations of AIFoundations of AI
Neuroscience (1861-present) How do brains process information
Psychology (1879 - Present) - investigating human mind How do humans and animals think and act?
Computer engineering (1940 - Present) - ever improving tools How can we build an efficient computer?
2004/03/24Sanz / Artificial Intelligence: An Introduction 8aslab
Foundations of AIFoundations of AI
Control theory and Cybernetics (1948-present) How can artifacts operate under their own control?
Linguistics (1957 - Present) - the structure and meaning of language How does language relate to thought?
2004/03/24Sanz / Artificial Intelligence: An Introduction 9aslab
What is Intelligence?What is Intelligence?
Intelligence, taken as a whole, consists of the following skills:
1. the ability to reason
2. the ability to acquire and apply knowledge
3. the ability to manipulate and communicate ideas
2004/03/24Sanz / Artificial Intelligence: An Introduction 10aslab
Has understanding/intentionality
Exhibits behaviour
SeeHearTouchTasteSmell
INPUTSINTERNAL PROCESSES
OUTPUTS
Senses environment
Can Reason
Has knowledge
An Intelligent EntityAn Intelligent Entity
2004/03/24Sanz / Artificial Intelligence: An Introduction 11aslab
The Age of Intelligent MachinesThe Age of Intelligent Machines
1st Industrial Revolution: the Age of Automation: Machines extend & multiply man's physical capabilities
2nd Industrial Revolution: the Age of Info Tech: Machines extend & multiply man's mental capabilities
Knowledge Revolution?: the Age of Knowledge Technology "..working smarter, not harder."
How do we make our systems smarter? - by building in intelligence?
2004/03/24Sanz / Artificial Intelligence: An Introduction 12aslab
More Definitions of AIMore Definitions of AI
AI is the science of making machines do things that would require intelligence if done by humansMarvin Minsky
AI is the part of computer science concerned with designing intelligent computer systemsEd Feigenbaum
Systems that can demonstrate human-like reasoning capability to enhance the quality of life and improve business competitivenessJapan-S’pore AI Centre
2004/03/24Sanz / Artificial Intelligence: An Introduction 13aslab
Behaviourist’s View on Intelligent MachinesBehaviourist’s View on Intelligent Machines
Many scientists believe that only things that can be directly observed are “scientific”
Therefore if a machine behaves “as if it were intelligent” it is meaningless to argue that this is an illusion.
Turing was of this opinion and proposed the “Turing Test”
This view can be summarized as:“If it walks like a duck, quacks like a duck and looks like a duck - it is a duck”
2004/03/24Sanz / Artificial Intelligence: An Introduction 14aslab
In 1950 Alan Turing published his now famous paper "Computing Machinery and Intelligence." In that paper he describes a method for humans to test AI programs.
In its most basic form, a human judge sits at a computer terminal and interacts with the subject by written communication only. The judge must then decide if the subject on the other end of the computer link is a human or an AI program imitating a human.
http://www.turing.org.uk/turing/
Turing’s TestTuring’s Test
2004/03/24Sanz / Artificial Intelligence: An Introduction 15aslab
Which one’s the man?
BA
Turing’s Test - Part 1Turing’s Test - Part 1
2004/03/24Sanz / Artificial Intelligence: An Introduction 16aslab
If the computer succeeds in fooling the judge then it has managed to exhibit a human level of intelligence in the task of pretending to be a woman, the definition of intelligence the machine has shown itself to be intelligent.
Which one’s the computer?
AB
Turing’s Test - Part 2Turing’s Test - Part 2
aslab 172004/03/24Sanz / Artificial Intelligence: An Introduction
Some History
From hype to work
2004/03/24Sanz / Artificial Intelligence: An Introduction 18aslab
Brief History of AIBrief History of AI
Gestation of AI (1943 -1955) McCulloch and Pitts’s model of artificial neurons Minsky’s 40-neuron network
Birth of AI (1956) A 2-month Dartmouth workshop of 10 attendees – the name
of AI Newell and Simon’ Logic Theorist
Early enthusiasm, great expectations (1952 - 1969) GPS by Newell and Simon, Lisp by McCarthy, Blockworld by
Minsky
2004/03/24Sanz / Artificial Intelligence: An Introduction 19aslab
Brief History of AIBrief History of AI
AI facing reality (1966 - 1973) Many predictions of AI coming successes
A computer would be a chess champion in 10 years (1957) Machine translation – Syntax is not enough Intractability of the problems attempted by AI
Knowledge-based systems (1969 - 1979) Knowledge is power, acquiring knowledge from experts Expert systems (MYCIN)
AI - an industry (1980 - present) Many AI systems help companies to save money and
increase productivity
2004/03/24Sanz / Artificial Intelligence: An Introduction 20aslab
Brief History of AIBrief History of AI
The return of neural networks (1986 – present) PDP books by Rumelhart and McClelland Connectionist models vs. symbolic models
AI – a science (1987 – present) Build on existing theories vs. propose brand new ones Rigorous empirical experiments Learn from data – data mining
AI – intelligent agents (1995 – present) Working agents embedded in real environments with
continuous sensory inputs
AI - conscious machines (Now !!) Making machines that feel and and have a self
2004/03/24Sanz / Artificial Intelligence: An Introduction 21aslab
Degree ofMotivation
DartmouthConference
AIWinter
Support Technology
Time1948 1970s - 80s mid-1980s
Japan 5thGeneration Computer
mid-1990s
History of AIHistory of AI
2004/03/24Sanz / Artificial Intelligence: An Introduction 22aslab
Examples of AI systemsExamples of AI systems
Robots Chess-playing program Voice recognition system Speech recognition system Grammar checker Pattern recognition Medial diagnosis System malfunction rectifier
Game Playing Machine Translation Resource Scheduling Expert systems (diagnosis,
advisory, planning, etc) Machine learning Intelligent interfaces
2004/03/24Sanz / Artificial Intelligence: An Introduction 23aslab
AI Case Study - RoboCupAI Case Study - RoboCup
The Robocup Competition pits robots (real and virtual) against each other in a simulated soccer tournament.
The aim of the RoboCup competition is to foster an interdisciplinary approach to robotics and agent-based AI by presenting a domain that requires large-scale co-operation and coordination in a dynamic, noisy, complex environment.
Common AI methods used are variants of neural networks and genetic algorithms.
aslab 242004/03/24Sanz / Artificial Intelligence: An Introduction
Intelligent Technologies
Resources for Sophisticated Information Processing
2004/03/24Sanz / Artificial Intelligence: An Introduction 25aslab
User
General Knowledge-baseInference engine
User interfacemay employ:
Question-and-Answer,
Menu-driven,
Naturallanguage,
GraphicsInterfaceStyles
Etc.
Knowledge-baseeditor
Explanationsubsystem
Case-specific data
Knowledge-Based Systems (KBS)Knowledge-Based Systems (KBS)
2004/03/24Sanz / Artificial Intelligence: An Introduction 26aslab
Synapse Neuron
Connectionbetween neurons
Outputs
Inputs
Plant
Sensors
InputOutput
Artificial Neural NetworksArtificial Neural Networks
What are Artificial Neural Networks (ANNs)? ANN or connecionist systems are systems that were developed based on
the learning characteristics of biological creatures. ANN solve problems though a process of learning and adaptation.
How are ANNs represented?
2004/03/24Sanz / Artificial Intelligence: An Introduction 27aslab
Genetic AlgorithmsGenetic Algorithms
We will use the processes loosely based on natural selection, crossover, and mutation to find solutions to certain problems.
GAs are adaptive (search, learning) methods based on the genetic processes of biological organisms.
A
1st generation of possible solutions
2nd generation of possible solutions
2004/03/24Sanz / Artificial Intelligence: An Introduction 28aslab
Fuzzy LogicFuzzy Logic
For systems with little complexity, hence little uncertainty, closed-form mathematical expressions provide precise description of the system.
For systems that are a little more complex, but for which significant data exists, model free methods such as artificial ANNs, provide a powerful and robust means to reduce uncertainty through learning.
For most complex systems where few numerical data exists and where only ambiguous or imprecise information may be available, fuzzy reasoning provides a way to understand system behavior.
Pre
cisi
on
in t
he
mo
del
Complexity (uncertainty) of the system
Mathematicalequations Model-free
Methods(e.g., ANNs)
Fuzzy Systems
aslab 292004/03/24Sanz / Artificial Intelligence: An Introduction
Towards intelligent machines
Are we ready to build the next generation of intelligent robots?
2004/03/24Sanz / Artificial Intelligence: An Introduction 30aslab
Some problems remain…Some problems remain…
Vision Audition / speech processing Natural language processing Touch, smell, balance and other senses Motor control
2004/03/24Sanz / Artificial Intelligence: An Introduction 31aslab
Computer PerceptionComputer Perception
Perception: provides an agent information about its environment. Generates feedback. Usually proceeds in the following steps.
Sensors: hardware that provides raw measurements of properties of the environment Ultrasonic Sensor/Sonar: provides distance data Light detectors: provide data about intensity of light Camera: generates a picture of the environment
Signal processing: to process the raw sensor data in order to extract certain features, e.g., color, shape, distance, velocity, etc.
Object recognition: Combines features to form a model of an object
And so on to higher abstraction levels
2004/03/24Sanz / Artificial Intelligence: An Introduction 32aslab
Perception for what?Perception for what?
Interaction with the environment, e.g., manipulation, navigation Process control, e.g., temperature control Quality control, e.g., electronics inspection, mechanical parts Diagnosis, e.g., diabetes Restoration, of e.g., buildings Modeling, of e.g., parts, buildings, etc. Surveillance, banks, parking lots, etc. … And much, much more
2004/03/24Sanz / Artificial Intelligence: An Introduction 33aslab
Sample perception: Computer visionSample perception: Computer vision
1. Grab an image of the object (digitize analog signal)
2. Process the image (looking for certain features)1. Edge detection2. Region segmentation3. Color analysis4. Etc.
3. Measure properties of features or collection of features (e.g., length, angle, area, etc.)
4. Use some model for detection, classification etc.
2004/03/24Sanz / Artificial Intelligence: An Introduction 34aslab
State of the artState of the art
Can recognize faces? – yes
Can find salient targets? – sure
Can recognize people? – no problem
Can track people and analyze their activity? – yep
Can understand complex scenes? – not quite but in progress
2004/03/24Sanz / Artificial Intelligence: An Introduction 35aslab
Face recognition case studyFace recognition case study
2004/03/24Sanz / Artificial Intelligence: An Introduction 36aslab
Pedestrian recognitionPedestrian recognition
2004/03/24Sanz / Artificial Intelligence: An Introduction 37aslab
How about other senses?How about other senses?
Speech recognition -- can achieve user-undependent recognition for small vocabularies and isolated words
Other senses -- overall excellent performance (e.g., using gyroscopes for sense of balance, or MEMS sensors for touch) except for olfaction and taste, which are very poorly understood in biological systems also.
2004/03/24Sanz / Artificial Intelligence: An Introduction 38aslab
How about actuationHow about actuation
Robots have been used for a long time in restricted settings (e.g., factories) and, mechanically speaking, work very well.
For operation in unconstrained environments, Biorobotics has proven a particularly active line of research:
Motivation: since animals are so good at navigating through their natural environment, let’s try to build robots that share some structural similarity with biological systems.
2004/03/24Sanz / Artificial Intelligence: An Introduction 39aslab
Robot examples: constrained environmentsRobot examples: constrained environments
2004/03/24Sanz / Artificial Intelligence: An Introduction 40aslab
Towards unconstrained environmentsTowards unconstrained environments
2004/03/24Sanz / Artificial Intelligence: An Introduction 41aslab
They’re here …They’re here …
Robot lawn mowers and vacuum-cleaners are here already…
2004/03/24Sanz / Artificial Intelligence: An Introduction 42aslab
The time is nowThe time is now
It is a particularly exciting time for AI because… CPU power is getting not a problem anymore Many physically-capable robots are available Some vision and other senses are partially available
Many AI algorithms for constrained environment are available
So for the first time we have all the components required to build smart robots that interact with the real world.
aslab 432004/03/24Sanz / Artificial Intelligence: An Introduction
Agents
Recent IA software focus
2004/03/24Sanz / Artificial Intelligence: An Introduction 44aslab
What is an Agent?What is an Agent?
in general, an entity that interacts with its environment perception through sensors actions through effectors or actuators
2004/03/24Sanz / Artificial Intelligence: An Introduction 45aslab
Examples of AgentsExamples of Agents
human agent eyes, ears, skin, taste buds, etc. for sensors hands, fingers, legs, mouth, etc. for effectors
powered by muscles
robot camera, infrared, bumper, etc. for sensors grippers, wheels, lights, speakers, etc. for effectors
often powered by motors
software agent functions as sensors
information provided as input to functions in the form of encoded bit strings or symbols
functions as effectors results deliver the output
2004/03/24Sanz / Artificial Intelligence: An Introduction 46aslab
Agents and Their ActionsAgents and Their Actions
a rational agent does “the right thing” the action that leads to the best outcome
problems: what is “ the right thing” how do you measure the “best outcome”
2004/03/24Sanz / Artificial Intelligence: An Introduction 47aslab
Performance of AgentsPerformance of Agents
criteria for measuring the outcome and the expenses of the agent often subjective, but should be objective task dependent time may be important
2004/03/24Sanz / Artificial Intelligence: An Introduction 48aslab
Performance Evaluation ExamplesPerformance Evaluation Examples
vacuum agent A number of tiles cleaned during a certain period
based on the agent’s report, or validated by an objective authority
doesn’t consider expenses of the agent, side effects energy, noise, loss of useful objects, damaged furniture,
scratched floor might lead to unwanted activities
agent re-cleans clean tiles, covers only part of the room, drops dirt on tiles to have more tiles to clean, etc.
2004/03/24Sanz / Artificial Intelligence: An Introduction 49aslab
Rational Agent considerationsRational Agent considerations
performance measure for the successful completion of a task
complete perceptual history (percept sequence) background knowledge
especially about the environment dimensions, structure, basic “laws”
task, user, other agents
feasible actions capabilities of the agent
2004/03/24Sanz / Artificial Intelligence: An Introduction 50aslab
OmniscienceOmniscience
a rational agent is not omniscient it doesn’t know the actual outcome of its actions it may not know certain aspects of its environment
rationality takes into account the limitations of the agent percept sequence, background knowledge, feasible actions it deals with the expected outcome of actions
2004/03/24Sanz / Artificial Intelligence: An Introduction 51aslab
Ideal Rational AgentIdeal Rational Agent
selects the action that is expected to maximize its performance based on a performance measure depends on the percept sequence, background knowledge,
and feasible actions
2004/03/24Sanz / Artificial Intelligence: An Introduction 52aslab
From Percepts to ActionsFrom Percepts to Actions
if an agent only reacts to its percepts, a table can describe the mapping from percept sequences to actions instead of a table, a simple function may also be used can be conveniently used to describe simple agents that
solve well-defined problems in a well-defined environment e.g. calculation of mathematical functions
2004/03/24Sanz / Artificial Intelligence: An Introduction 53aslab
Agent or ProgramAgent or Program
our criteria so far seem to apply equally well to software agents and to regular programs
autonomy agents solve tasks largely independently programs depend on users or other programs for “guidance” autonomous systems base their actions on their own
experience and knowledge requires initial knowledge together with the ability to learn provides flexibility for more complex tasks
2004/03/24Sanz / Artificial Intelligence: An Introduction 54aslab
Structure of Intelligent AgentsStructure of Intelligent Agents
Agent = Architecture + Program architecture
operating platform of the agent computer system, specific hardware, possibly OS functions
program function that implements the mapping from percepts to
actions
2004/03/24Sanz / Artificial Intelligence: An Introduction 55aslab
Software AgentsSoftware Agents
also referred to as “softbots” live in artificial environments where computers and
networks provide the infrastructure may be very complex with strong requirements on the
agent World Wide Web, real-time constraints,
natural and artificial environments may be merged user interaction sensors and effectors in the real world
camera, temperature, arms, wheels, etc.
2004/03/24Sanz / Artificial Intelligence: An Introduction 56aslab
Agent Program TypesAgent Program Types
different ways of achieving the mapping from percepts to actions
different levels of complexity
simple reflex agents agents that keep track of the world goal-based agents utility-based agents
2004/03/24Sanz / Artificial Intelligence: An Introduction 57aslab
Simple Reflex AgentsSimple Reflex Agents
instead of specifying individual mappings in an explicit table, common input-output associations are recorded requires processing of percepts to achieve some abstraction frequent method of specification is through condition-action
rules if percept then action
similar to innate reflexes or learned responses in humans efficient implementation, but limited power
2004/03/24Sanz / Artificial Intelligence: An Introduction 58aslab
Sensors
Effectors
What the world is like now
What should I do now
Condition-action rules
Agent
En
viro
nm
ent
Reflex Agent DiagramReflex Agent Diagram
2004/03/24Sanz / Artificial Intelligence: An Introduction 59aslab
Reflex Agent with Internal StateReflex Agent with Internal State
an internal state maintains important information from previous percepts sensors only provide a partial picture of the environment
2004/03/24Sanz / Artificial Intelligence: An Introduction 60aslab
Sensors
Effectors
What should I do now
State
How the world evolves
What my actions do
Agent
Environment
Condition-action rules
What the world is like now
Agent with State DiagramAgent with State Diagram
2004/03/24Sanz / Artificial Intelligence: An Introduction 61aslab
Goal-Based AgentGoal-Based Agent
the agent tries to reach a desirable state may be provided from the outside (user, designer), or
inherent to the agent itself
results of possible actions are considered with respect to the goal may require search or planning
very flexible, but not very efficient
2004/03/24Sanz / Artificial Intelligence: An Introduction 62aslab
Sensors
Effectors
What the world is like now
What happens if I do an action
What should I do now
State
How the world evolves
What my actions do
Goals
Agent
Goal-Based Agent DiagramGoal-Based Agent Diagram
2004/03/24Sanz / Artificial Intelligence: An Introduction 63aslab
Utility-Based AgentUtility-Based Agent
more sophisticated distinction between different world states states are associated with a real number
may be interpreted as “degree of happiness” allows the resolution of conflicts between goals permits multiple goals
2004/03/24Sanz / Artificial Intelligence: An Introduction 64aslab
Sensors
Effectors
What the world is like now
What happens if I do an action
How happy will I be then
What should I do now
State
How the world evolves
What my actions do
Utility
Agent
Utility-Based Agent DiagramUtility-Based Agent Diagram
2004/03/24Sanz / Artificial Intelligence: An Introduction 65aslab
EnvironmentsEnvironments
determine to a large degree the interaction between the “outside world” and the agent the “outside world” is not necessarily the “real world” as we
perceive it
in many cases, environments are implemented within computers they may or may not have a close correspondence to the
“real world”
2004/03/24Sanz / Artificial Intelligence: An Introduction 66aslab
Environment PropertiesEnvironment Properties
accessible vs. inaccessible sensors provide all relevant information
deterministic vs. non-deterministic changes in the environment are predictable
episodic vs. non-episodic independent perceiving-acting episodes
static vs. dynamic no changes while the agent is “thinking”
discrete vs. continuous limited number of distinct percepts/actions
2004/03/24Sanz / Artificial Intelligence: An Introduction 67aslab
Agents SummaryAgents Summary
agents perceive and act in an environment ideal agents maximize their performance measure autonomous agents act independently
basic agent types simple reflex reflex with state goal-based utility-base
some environments may make life harder for agents inaccessible, non-deterministic, non-episodic, dynamic,
continuous
aslab 682004/03/24Sanz / Artificial Intelligence: An Introduction
References
Basic literature
2004/03/24Sanz / Artificial Intelligence: An Introduction 69aslab
Recommended BooksRecommended Books
Artificial Intelligence : A Modern Approach by Stuart J. Russell, Peter Norvig
Logical Foundations of Artificial Intelligence by Michael R. Genesereth, Nils J. Nislsson, Nils J. Nilsson
Artificial Intelligence by Patrick Henry Winston Artificial Intelligence by Elaine Rich, Kevin Knight (good for
logic, knowledge representation, and search only)
2004/03/24Sanz / Artificial Intelligence: An Introduction 70aslab
General ReferenceGeneral Reference
Whatis.com (Computer Science Dictionary)http://whatis.com/search/whatisquery.html
Technology Encyclopediahttp://www.techweb.com/encyclopedia/
Computing Dictionaryhttp://wombat.doc.ic.ac.uk/
Webster Dictionaryhttp://work.ucsd.edu:5141/cgi-bin/http_webster