Artificial Intelligence
CSE643
Lecture #2
Tip: Take your own notes during lectures
C. Anantaram
c.anantaram@iiitd.ac.in
Google classroom code: dke4bgy
Note: This session is being recorded.
Disclaimer: I do not claim that all material in these slides are self-produced.
Some Material for the slides are taken from internet and other sources.
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
(yet)
• Special-purpose AI is more doable (nontrivial)
• E.g., chess/poker/Go playing programs, logistics planning, automated
translation, speech and image recognition, web search, data mining,
medical diagnosis, keeping a car on the road, … … … …
From Vincent Conitzer’s slides on Artificial Intelligence, Duke University 2
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf 3
Focus of AI
Systems that think like Systems that think
focus on action humans rationally
sidesteps philosophical
Systems that act like Systems that act
issues such as “is the
humans rationally
system conscious” etc.
• A lot of AI systems mostly 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
From Stuart Russell’s book, and Vincent Conitzer’s slides on Artificial Intelligence, Duke University 4
AI pre-history
• Philosophy Logic, methods of reasoning, mind as physical
system foundations of learning, language,
rationality
• Mathematics Formal representation and proof algorithms,
computation, (un)decidability, (in)tractability,
probability
• Economics utility, decision theory
• Neuroscience physical substrate for mental activity
• Psychology phenomena of perception and motor control,
experimental techniques
• Computer building fast computers
engineering
• Control theory design systems that maximize an objective
function over time
• Linguistics knowledge representation, grammar
5
History of AI
• The history of AI begins with the following articles:
• Turing, A.M. (1950), Computing machinery and intelligence, Mind, Vol.
59, pp. 433-460.
From Xiao-Jun Zeng’s AI fundamentals slides, Univ of Manchester 6
History of AI – Acting Humanly: Turing Test
• Turing (1950) "Computing machinery and intelligence":
• "Can machines think?" → "Can machines behave intelligently?"
• Operational test for intelligent behavior: the Imitation Game
• Human beings are intelligent
• To be called intelligent, a machine must produce responses that are indistinguishable from those
of a human
From Max Welling: Introduction to AI course
7
and some parts from Eakta Jain’s slides
Is Turing Test the right goal?
• “Aeronautical engineering texts do not define the goal of their field as
making ‘machines that fly so exactly like pigeons that they can fool
even other pigeons.’” [Russell and Norvig]
From Vincent Conitzer’s slides on Artificial Intelligence, Duke University 8
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf 9
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf 10
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf 11
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf 12
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf 13
Areas of AI
• The rigorous application of probability theory and statistics in AI generally gained
in popularity in the 1990s and are now the dominant paradigm in:
• Machine learning
• Pattern recognition and machine perception, e.g.,
• Computer vision
• Speech recognition
• Robotics
• Natural language processing
14
From Xiao-Jun Zeng’s AI fundamentals slides, Univ of Manchester
Areas of AI
• Deduction, reasoning, problem solving such as
• Theorem-provers, solve puzzles, play board games
• Knowledge representation systems such as
• Expert systems
• Automated planning and scheduling
• Machine Learning and Perception such as
• detecting credit card fraud, stock market analysis, classifying DNA sequences, speech and handwriting
recognition, object and facial recognition in computer vision
• Natural language processing such as
• Natural Language Understanding
• Speech Understanding
• Language Generation
• Machine Translation
• Information retrieval and text mining
• Motion and manipulation such as
• Robotics to handle such tasks as object manipulation and navigation, with sub-problems of localization
(knowing where you are), mapping (learning what is around you) and motion planning (figuring out how to
get there)
• Social and business intelligence such as
• Social and customer behaviour modelling
15
From Xiao-Jun Zeng’s AI fundamentals slides, Univ of Manchester
Areas of AI
16
Some areas where humans shine
• Coming up with reasonably good solutions in complex messy environments
• Adapting/self-evaluation/creativity (“My usual approach to chess is getting
me into trouble against this person… Why? Is there something entirely
different I can do?”)
• Analogical reasoning, transfer learning (applying insights from one domain
to another)
• Explaining our reasoning
• Tasks that require a broad understanding of the (human) world
• Knowing what it’s like to be human
• Humor
•…
From Vincent Conitzer’s slides on Artificial Intelligence, Duke University 17
Modern AI
• AI achieved its greatest successes, albeit somewhat behind the
scenes, due to:
• the incredible power of computers today
• a greater emphasis on solving specific subproblems
• the creation of new ties between AI and other fields working on similar
problems
• a new commitment by researchers to solid mathematical methods and
rigorous scientific standards, in particular, based probability and
statistical theories
• Significant progress has been achieved in neural networks, probabilistic
methods for uncertain reasoning and statistical machine learning,
machine perception (computer vision and Speech), optimisation and
evolutionary computation, fuzzy systems, Intelligent agents
18
What is Artificial Intelligence ?
Behaviour
• Has Knowledge; Uses it
• Man-made • Understanding
• Simulated • Reasoning
• Not natural • Learning
• Ability to solve problems 19
Purpose of AI
• Making the computer do more complex tasks in the real-world
• Use computers for decision-making
• Higher abstraction of programming
20
Definition of AI
• “AI is the science and engineering of making intelligent machines which can
perform tasks that require intelligence when performed by humans …”
• Computer science defines AI research as the study of "intelligent agents":
any device that perceives its environment and takes actions that maximize
its chance of successfully achieving its goals.
• A more elaborate definition characterizes AI as “a system’s ability to
correctly interpret external data, to learn from such data, and to use those
learnings to achieve specific goals and tasks through flexible adaptation.”
21
Characteristics of AI systems
• Knowledge
• Explicit
• Implicit
• Reasoning
• Explicit
• Implicit
• Learning
• Explicit
• Generalization
• Specialization
• Implicit
• Generalization
• Specialization
22
Basic problems
• Base machine is computational.
• No prior knowledge. Has to be specified.
• Cannot say machine has understood.
• Reasoning absent. Has to be built.
• No commonsense. No intuition
• Learning can only be simulated
• Constrained by whatever knowledge and data that we seed
• No General Knowledge
23
Some properties of AI systems
• Capture knowledge
• Simulate experience
• Reasoning by the System
• Inductive, Deductive and Abductive
• Searching for a solution
• Learning 24
Aspects in building modern AI solutions
• Data
• Lots of it and more being generated
• Hidden patterns, hidden correlations
• Tremendous variations
• Knowledge
• Explicit knowledge – in terms of rules, cases, frames, scripts
• Implicit knowledge – tacit knowledge – cannot be expressed explicitly
• Reasoning
• Explicit reasoning – logic based, similarity-based, probabilistic-based
• Implicit reasoning – pattern-based, infer relations, deep-reasoning
• Learning
• Deriving specializations
• Finding generalizations 25
Intelligent Agents
• Agents and environments
• Rationality
• PEAS – Performance, Environment, Actuators and Sensors
• Environment types
• Agent types
26
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf
Rational behaviour
27
Agents
• Agent: An agent is anything that can be viewed as perceiving its
environment through sensors and acting upon that environment
through actuators
• Human agent: eyes, ears, and other organs for sensors; hands, legs,
mouth, and other body parts for actuators
• Robotic agent: cameras and infrared range finders for sensors;
various motors for actuators
• Software agent: receives keystrokes, file contents, network packets as
sensory inputs and acts by displaying, writing files, sending network
packets, etc.
28
Agent
29
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf
Agent = Architecture + Program
30
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf
Example: Vacuum cleaner world
31
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf
A vacuum cleaner agent
32
A vacuum cleaner agent
33
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf
A vacuum cleaner agent
34
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf
Designing Agents
35
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf
Agents: Performance measurement
• An agent should strive to "do the right thing", based on what it can
perceive and the actions it can perform. The right action is the one
that will cause the agent to be most successful
• Performance measure: An objective criterion for success of an agent's
behavior
• E.g., performance measure of a vacuum‐cleaner agent could be
amount of dirt cleaned up, amount of time taken, amount of
electricity consumed, amount of noise generated, etc
36
From https://cs.brynmawr.edu/Courses/cs372/fall2017/IntroducingAI2.pdf
References
• Chapter 1: Russell and Norvig’s book
• Chapter 1: Deepak Khemani’s book
• Chapter 2: Russell and Norvig
37
