Download - RehanCodes

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Visual Turing Test wikipedia , lookup

AI winter wikipedia , lookup

Ecological interface design wikipedia , lookup

Agent (The Matrix) wikipedia , lookup

Wizard of Oz experiment wikipedia , lookup

Technological singularity wikipedia , lookup

Artificial intelligence in video games wikipedia , lookup

Adaptive collaborative control wikipedia , lookup

Human–computer interaction wikipedia , lookup

Knowledge representation and reasoning wikipedia , lookup

Intelligence explosion wikipedia , lookup

Embodied cognitive science wikipedia , lookup

History of artificial intelligence wikipedia , lookup

Philosophy of artificial intelligence wikipedia , lookup

Existential risk from artificial general intelligence wikipedia , lookup

Ethics of artificial intelligence wikipedia , lookup

Transcript
Artificial Intelligence
Introduction
Ms. Amna Khan
Text Book
Text Book 1: Artificial Intelligence: A
Modern Approach 3 edition.
Authors: Stuart Russell and Peter Norvig.
ISBN-13: 978-0136042594
Text Book 2: Artificial Intelligence:
Structures and Strategies for Complex
Problem Solving 6th edition.
Authors: George F luger.
rd
Grading
What is artificial intelligence?
Popular conception driven by science fiction
◦ Robots good at everything except emotions, empathy,
appreciation of art, culture, …
◦ … until later in the movie.
◦ Current AI is also bad at lots of simpler stuff!
◦ There is a lot of AI work on thinking about what other
agents are thinking
Real AI
A serious science.
General-purpose AI like the robots of science fiction is
incredibly hard
◦ Human brain appears to have lots of special and general functions,
integrated in some amazing way that we really do not understand at all
(yet)
Special-purpose AI is more doable (nontrivial)
◦ E.g., chess/poker playing programs, logistics planning, automated
translation, voice recognition, web search, data mining, medical
diagnosis, keeping a car on the road, … … … …
Examples of Artificial Intelligence
You’re Using in Daily Life
 Virtual Personal Assistants
Siri, Google Now, and Cortana are all intelligent digital
personal assistants on various platforms (iOS, Android, and
Windows Mobile).
Voice Recognition Enabled :
Help find useful information when you ask for it using your
voice; you can say “Where’s the nearest mart?”, “What’s on
my schedule today?”, “Remind me to call Jerry at eight
o’clock,” and the assistant will respond by finding information,
relaying information from your phone, or sending commands
to other apps.
Examples of Artificial Intelligence
You’re Using in Daily Life
 Video Games
 One of the instances of AI that most people are probably familiar with,
video game AI has been used for a very long time—since the very first
video games.
But the complexity and effectiveness of that AI has increased
exponentially over the past several decades, resulting in video game
characters that learn your behaviors, respond to stimuli, and react in
unpredictable ways.
 2014’s Middle Earth: Shadow of Mordor is especially notable for the
individual personalities given to each non-player character, their
memories of past interaction, and their variable objectives.
Examples of Artificial Intelligence
You’re Using in Daily Life
 First-person shooters like Far Cry and Call of Duty also
make significant use of AI, with enemies that can analyze
their environments to find objects or actions that might be
beneficial to their survival; they’ll take cover, investigate
sounds, use flanking maneuvers, and communicate with
other AIs to increase their chances of victory.
As far as AI goes, video games are somewhat simplistic,
but because of the industry’s huge market, a great deal of
effort and money are invested every year in perfecting this
type of AI.
Examples of Artificial Intelligence
You’re Using in Daily Life
Smart Cars
 You probably haven’t seen someone reading the
newspaper while driving to work yet, but self-driving
cars are moving closer and closer to reality; Google’s
self-driving car project and Tesla’s “autopilot” feature
are two examples that have been in the news lately.
 Google has developed an algorithm that could
potentially let self-driving cars learn to drive in the same
way that humans do: through experience.
Examples of Artificial Intelligence
You’re Using in Daily Life
Purchase Prediction
 Large retailers like Target and Amazon stand to make a
lot of money if they can anticipate your needs.
 Amazon’s anticipatory shipping project hopes to send
you items before you need them, completely obviating
the need for a last-minute trip to the online store.
 While that technology isn’t yet in place, brick-andmortar retailers are using the same ideas with coupons;
when you go to the store, you’re often given a number
of coupons that have been selected by a predictive
analytics algorithm.
Examples of Artificial Intelligence
You’re Using in Daily Life
 Smart Home Devices
 Many smart home devices now include the ability to learn
your behavior patterns and help you save money by adjusting
the settings on your thermostat or other appliances in an
effort to increase convenience and save energy.
 For example, turning your oven on when you leave work
instead of waiting to get home is a very convenient ability. A
thermostat that knows when you’re home and adjusts the
temperature accordingly can help you save money by not
heating the house when you’re out.
Definitions of AI
Focus on action avoids
philosophical issues
such as “is the system
conscious” etc.
if our system can be more
rational than humans in
some cases, why not?
Systems that think Systems that think
like humans
rationally
Systems that act
like humans
Systems that act
rationally
Definitions of AI
• We will follow “act rationally” approach
– Distinction may not be that important
• acting rationally/like a human presumably requires
(some sort of) thinking rationally/like a human,
• humans much more rational anyway in complex
domains
Lessons from AI research
Clearly-defined tasks that we think require intelligence and
education from humans tend to be doable for AI
techniques
◦ Playing chess, drawing logical inferences from clearly-stated facts,
performing probability calculations in well-defined environments,
…
◦ Although, scalability can be a significant issue
Complex, messy, ambiguous tasks that come natural to
humans (in some cases other animals) are much harder
◦ Recognizing your grandmother in a crowd, drawing the right
conclusion from an ungrammatical or ambiguous sentence,
driving around the city, …
Lessons from AI research
Humans better at coming up with reasonably
good solutions in complex environments
Humans better at adapting/selfevaluation/creativity (“My usual strategy for
chess is getting me into trouble against this
person… Why? What else can I do?”)
Turing Test
(Human) judge communicates with a human and a
machine over text-only channel,
Both human and machine try to act like a human,
Judge tries to tell which is which.
Numerous variants
image from http://en.wikipedia.org/wiki/Turing_test
Turing Test on unsuspecting judges
It is possible to (temporarily) fool humans who do not
realize they may be talking to a bot
ELIZA program [Weizenbaum 66] rephrases partner’s
statements and questions (~psychotherapist)
Turing Test
The Computer would need to possess the following
capabilities:
 Natural language processing to enable it to communicate
successfully in English (or some other human language)
Knowledge representation to store information provided
before or during the interrogation;
 Automated reasoning to use the stored information to
answer questions and to draw new conclusions
 Machine learning to adapt to new circumstances and to
detect and extrapolate patterns.
The interdisciplinary field of cognitive
science brings together computer models
from AI and experimental techniques from
psychology to try to construct precise and
testable theories of the workings of the
human mind.
Acting rationally: The rational
agent approach
 Acting rationally means acting so as to achieve
one's goals, given one's beliefs.
 An agent is just something that perceives and
acts. (This may be an unusual use of the word,
but you will get used to it.)
 In this approach, AI is viewed as the study and
construction of rational agents.
Acting rationally: The rational
agent approach
 Making correct inferences is sometimes part of
being a rational agent, because one way to act
rationally is to reason logically to the conclusion
that a given action will achieve one's goals, and
then to act on that conclusion.
 On the other hand, correct inference is not all
of rationality, because there are often situations
where there is no provably correct thing to do,
yet something must still be done.
Acting rationally: The rational
agent approach
There are also ways of acting rationally that cannot be
reasonably said to involve inference. For example,
pulling one's hand off of a hot stove is a reflex action
that is more successful than a slower action taken after
careful deliberation.
AI as rational agent :advantages
 First, it is more general than the "laws of
thought" approach, because correct inference is
only a useful mechanism for achieving rationality,
and not a necessary one.
 Second, it is more amenable to scientific
development than approaches based on human
behavior or human thought, because the standard
of rationality is clearly defined and completely
general.
Robots vs. Other Intelligent
Agents
•In AI, artificial agents that have a physical presence in the world are
usually known as robots
◦ Robotics is the field primarily concerned with the implementation of the
physical aspects of a robot
◦ I.e., perception of and action in the physical environment
◦ Sensors and actuators
•
Agents without a physical presence: software agents
◦ E.g. desktop assistants, decision support systems, web crawlers, text-based
translation systems, intelligent tutoring systems, etc
◦ They also interact with an environment, but not the physical world
•Software agents and robots
◦ differ in their interaction with the environment
◦ share all other fundamental components of intelligent behavior
24
Intelligent Agents in the World
Knowledge Representation
Machine Learning
abilities
Reasoning +
Decision Theory
Natural Language
Generation
Natural Language
Understanding
+
Computer Vision
Speech Recognition
+
Physiological Sensing
Mining of Interaction Logs
+
Robotics
+
Human Computer
/Robot
Interaction
Representation and Reasoning
To use these inputs an agent
needs to represent them
 knowledge
One of AI goals: specify how
a system can Acquire and
represent knowledge
about a domain
(representation)
• Use the knowledge to
solve problems in that
domain (reasoning)
Representation
& Reasoning
Representation and Reasoning (R&R) System
•A representation language to describe
◦ The environment
◦ Problems (questions/tasks) to be solved
•Computational reasoning procedures to compute a solution to a
problem
◦ E.g., an answer, sequence of actions
problem ⟹ representation ⟹ computation⟹ representation ⟹ solution
•Choice of an appropriate R&R system depends on various
dimensions, e.g. properties of
• the environment, the type of problems, the agent, the computational
resources, etc.
27
Representational Dimensions
Environment
Problem Type
Static
Sequential
Deterministic
Stochastic
We’ll start by
Each cell will include a R&R
describing
system covered in the
dimensions
courserelated
to the problem and
environment
Then we’ll include in each
Then
cellwe’ll
the various
include R&R
in each
cell
systems
R&R system
coveredcovered
in the
course,inand
the discuss
course some
more dimensions