Artificial Intelligence –
Warm-up (Unit I)
Jay R. Bhatnagar
To Add during class lecture ……
• Venn Diagram view of H - C worlds: representation (up link:
transmitter), cognition/ classification (down link: receiver)
• AI Pyramid
Introduction to Artificial Intelligence(AI)
Artificial Intelligence are the
development of computer systems that
are capable of performing tasks that
require human intelligence,
Eg: Decision making, Object detection,
Solving complex problems etc.
Figure Source: Edureka
We call programs intelligent if they exhibit behaviors that would be
Herbert regarded intelligent if they were exhibited by human beings : close to
Turing
Simon
Avron Barr Physicists ask what kind of place this universe is and seek to
and characterize its behavior systematically. Biologists ask what it
means for a physical system to be living. We in AI wonder
Some definitions Edward
Feigenbaum
what kind of information-processing system – “can machines
ask questions like humans do”
Elaine Rich AI is the study of techniques for solving exponentially hard
problems in polynomial time by exploiting knowledge about
the problem domain. - “What AI does”
Eugene
AI is the study of mental faculties through the use of computational
Charniak and models - ?
Drew
McDermott
Rational
Decisions
Definition of AI
• Existing definitions advocate everything from replicating human
intelligence to simply solving knowledge-intensive tasks.
Examples:
“Artificial Intelligence is the design, study and construction of
computer programs that behave intelligently.” -- Tom Dean.
“Artificial Intelligence is the enterprise of constructing a physical
symbol system that can reliably pass the Turing test.” -- Matt
Ginsberg.
6
Introduction to Artificial Intelligence
• Philosophy of AI - “Can a machine think and behave like humans do?”
• In Simple Words - Artificial Intelligence is a way of making a computer, a computer-controlled robot, or a
software think intelligently, in the similar manner the intelligent humans think.
• Artificial intelligence (AI) is an area of computer science that emphasizes the creation of intelligent
machines that work and re-act like humans.
• AI is accomplished by studying how human brain thinks, and how humans learn, decide, and work while trying
to solve a problem, and then using the outcomes of this study as a basis of developing intelligent software and
systems.
• AI ( My definition):
Design of data centric, human interactive – interpretable – explainable intelligence (hardware - software solutions)
using symbols, rules and language for machine systems which smoothens learning steps (new discrete steps or
informative steps) of Machine logic (discrete step or output states) and assists in reliable processing of
information from short instances (modularity) of unstructured random data, whilst earlier machines were mostly
used to developing automation or inference ( quantitative, graphical, text, sentiment) through generalized data
structures, well-defined or crisp logic & large data aggregates.
7
Generalizing from Data : Machine Learning, Generalizing from Machine and Human Expert: AI
• We’ll use the term rational in a very specific, technical
way
– Rational: maximally achieving pre-defined goals
– Rationality only concerns what decisions are made
Rational (not the thought process behind them)
– Goals are expressed in terms of the utility of
Decisions outcomes
– Being rational means maximizing your expected
utility
• Computational Rationality
Turing Test
Approach
Introduced by Alan Turing (1950)
THINK HUMANLY &
ACT HUMANLY
Foundations of Artificial Intelligence
Below are the disciplines that contributed ideas, viewpoints and
techniques to AI:mcq
1. Philosophy
2. Mathematics
3. Economics
4. Neuroscience
5. Psychology
6. Computer Engineering
7. Control theory, Linguistics 10
Agent &
Environment
• ‘Anything’ that can gather information
about its environment and take action
based on that information.
• In AI, an intelligent agent (IA) is
an autonomous entity which observes
through sensors and acts upon
an environment using actuators and directs
its activity towards achieving goals.
• Intelligent agents may also learn or
use knowledge to achieve their goals.
• A rational agent is one that acts so as to
achieve the best outcome or, when there is
uncertainty, the best expected outcome.
AI Agents
• A human agent
• eyes, ears, and other organs for sensors
• hands, legs, vocal tract, and so on for actuators.
• A robotic agent
• might have cameras and infrared range finders for sensors
• various motors for actuators.
• A software agent
• receives keystrokes, file contents, and network packets as sensory inputs
• acts on the environment by displaying on the screen, writing files, and
sending network packets.
Agent
…
• Percept – Concept + Hypothesis + Instances refers to the agent’s
perceptual inputs at any given instant.
• An agent’s percept sequence is the complete history of everything the
agent has ever perceived.
• An agent’s choice of action at any given instant can depend on the entire
percept sequence observed to date, but not on anything it hasn’t
perceived.
• Mathematically speaking, we say that an Agent’s behavior is described by
the agent function that maps any given percept sequence to an action
• One could view a hand-held calculator as an agent that chooses the action
of displaying “4” when given the percept sequence “2 + 2 =,”
Knowledge (Data, Function) – AI looks to
Data Scientist
Jay R. Bhatnagar
Components of AI Engine
Components of Expert Systems / AI internal
• Knowledge Base
• Inference Engine
• User Interface
Internals AI Engine: Transfer Learning
Learning “Rules” only – Production type AI
Thanks - End of Slides
* Department of CSE, GIT Course Code and Course Title:19EID134 AI Tools. 18