CE 451: Applied Artificial Intelligence

Lecture 2 - Introduction

Instructor: Dr. Hashim Ali

Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi
[Spring 2019]
CE451 Applied Artificial Intelligence

A Quick overview of last lecture

 Course information

 Course material available on Google drive (link sent to?)

 AI – Robots only? (Hollywood Sci-Fi)

 AI – in reality – Think and act rationally

 Rationally  maximizing an objective

 Brain vs AI  lessons learnt (memory and simulation)

Lecture 02 - Introduction
CE451 Applied Artificial Intelligence

A (Short) History of AI

Lecture 02 - Introduction
CE451 Applied Artificial Intelligence

A (Short) History of AI
 1940-1950: Early days
• 1943: McCulloch & Pitts: Boolean circuit model of brain
• 1950: Turing's “Computing Machinery and Intelligence”
 1950—65: Excitement: Look, Ma, no hands!
• 1950s: Early AI programs, including Samuel's checkers program,
Newell & Simon's Logic Theorist General Problem Solver (GPS),
Gelernter's Geometry Engine, McCarthy’s invention of LISP.
• 1956: Dartmouth meeting: “Artificial Intelligence” adopted
• 1965: Robinson's complete algorithm for logical reasoning
 1966—73: Reality dawns
• Realization that many AI problems are intractable.
• Limitations of existing neural network methods identified.
• Neural network research almost disappears.
 1970—90: Knowledge-based approaches
• 1969—79: Early development of knowledge-based systems
• 1980—88: Success of rule-based expert systems - DENDRAL, MYCIN.
• 1988—93: Expert systems industry busts: “AI Winter” as expert
systems are brittle and did not scale well in practice.

Lecture 02 - Introduction
CE451 Applied Artificial Intelligence

A (Short) History of AI
 1986: Rise of machine learning
• Neural networks return to popularity
• Major advances in machine learning algorithms and applications.
 1990s: Statistical approaches
• Resurgence of probability, focus on uncertainty
• General increase in technical depth
• Bayesian networks
• Agents and learning systems… “AI Spring”?
 1995: AI as Science
• Integration of learning, reasoning, and knowledge representation
• AI methods used in vision, language, data mining, etc.

 2000s: Where are we now?

• More rigorous, formal, mathematical
• Fewer grandiose promises
• More directly connected to neighboring disciplines.
 Cognitive science.
 Statistics and Economics.
 Biology
 Psychology, etc.

Lecture 02 - Introduction
CE451 Applied Artificial Intelligence

Current State of AI
 How complicated is our brain?
• A neuron or nerve cell, is the basic information
processing unit.
• Estimated to be on the order of 1012 neurons in a
human brain.
• Many more synapses (1014) connect these neurons.
• Cycle time: 10-3 second (1 millisecond)
 How complex computers can we make?
• Supercomputer: hundreds of CPUs, 1012 bits of RAM.
• Cycle time: order of 10-9 seconds.
 Conclusion
• Yes: in the near future, we can have computers with as
many basic processing elements as our brain but with
 Far fewer interconnections (wires or synapses) than the brain.
 Much faster updates than the brain
 But building hardware is very different from making a computer behave like
a brain!

Lecture 02 - Introduction
CE451 Applied Artificial Intelligence

What this course is about?

 This is a course to introduce strategies, methods and algorithms for solving
problems that require decision making on the part of the computer.

 AI from Hollywood is NOT AI in real world (though we are catching up … but

still a long way to go).

 At the end of this course, you will be familiar with the fundamentals of
different approaches used for decision making, e.g., playing a game, find
the best route, ranking your choices, classifying objects, etc.

Lecture 02 - Introduction
CE451 Applied Artificial Intelligence

What this course is about?

Lecture 02 - Introduction
CE451 Applied Artificial Intelligence

What Can AI Do?

Quiz: Which of the following can be done at present?

 Play a decent game of table tennis?

 Play a decent game of Chess?
 Drive safely along a curving mountain road?
 Drive safely along Islamabad Expressway?
 Buy a week's worth of groceries on the web?
 Buy a week's worth of groceries at Metro, Islamabad?
 Discover and prove a new mathematical theorem?
 Converse successfully with another person for an hour?
 Perform a surgical operation?
 Put away the dishes and fold the laundry?
 Translate spoken Chinese into spoken English in real time?
 Write an intentionally funny story?

Lecture 02 - Introduction
 CE451 Applied Artificial Intelligence

Unintentionally Funny Stories

 One day Joe Bear was hungry. He asked his friend
Irving Bird where some honey was. Irving told him
there was a beehive in the oak tree. Joe walked to
the oak tree. He ate the beehive. The End.

 Henry Squirrel was thirsty. He walked over to the

river bank where his good friend Bill Bird was sitting.
Henry slipped and fell in the river. Gravity drowned.
The End.

 Once upon a time there was a dishonest fox and a vain crow. One day the
crow was sitting in his tree, holding a piece of cheese in his mouth. He noticed
that he was holding the piece of cheese. He became hungry, and swallowed
the cheese. The fox walked over to the crow. The End.
[Shank, Tale-Spin System, 1984]
Lecture 02 - Introduction
CE451 Applied Artificial Intelligence

Natural Language
 Speech technologies (e.g. Siri)
• Automatic speech recognition (ASR)
• Text-to-speech synthesis (TTS)
• Dialog systems

Lecture 02 - Introduction
 CE451 Applied Artificial Intelligence

References & Acknowledgements

 Partially adapted from lecture slides from Stanford University, UCIrvine, and UC
Berkeley.
 Some videos taken from UC Berkeley website.
 Contents from George F. Luger, AI: Structures and strategies for complex problem
solving, 6th Ed.

Lecture 02 - Introduction