Fair Use Notice

The material used in this presentation i.e., pictures/graphs/text, etc. is solely

intended for educational/teaching purpose, offered free of cost to the students for
use under special circumstances of Online Education due to COVID-19 Lockdown
situation and may include copyrighted material - the use of which may not have
been specifically authorised by Copyright Owners. It’s application constitutes Fair
Use of any such copyrighted material as provided in globally accepted law of many
countries. The contents of presentations are intended only for the attendees of the
class being conducted by the presenter.

1
 MEHRAN UNIVERSITY OF ENG. & TECH., JAMSHORO
DEPARTMENT OF MECHANICAL ENGINEERING
B.E. MECHATRONIC ENGINEERING
CS 491- MACHINE INTELLIGENCE
for F16 MTE

PART 1 INTRODUCTION

Slides adapted from:

CS 188: Artificial Intelligence, University of California, Berkeley & VU CS 607

2
 Textbook

Russell & Norvig, AI: A Modern Approach, 3rd Ed.

3
AI

4
5
6
AI

7
 Intelligence
o Are the things shown below, Intelligent?

8
Ex-1: Searching a path …

Different mice might follow different paths based to their intelligence

In other words: The problem can be solved in many ways
Ability to solve problems demonstrates Intelligence
9
 Ex-2: Next number in the
sequence …
o Consider the following sequence …
1,3,7,13,21,__
oWhat is the next number ?

• Key: Adding the next EVEN number …

1+2 = 3; 3+4 = 7; 7+6 = 13; 13+8 =21; 21+10 = 31
1,3,7,13,21,31

Ability to solve problems demonstrates

Intelligence 10
 So, Let’s Summarize…
Intelligence is:
o Ability to solve problems
o Ability to plan and schedule
o Ability to memorize and process information
o Ability to answer fuzzy questions
o Ability to learn
o Ability to recognize
o Ability to understand
o Ability to perceive
o And many more …
Food for thought: Can only humans beings and animals possess 11
these qualities?
 What if?
o A machine searches through a mesh and finds a path?
o A machine solves problems like the next number in
the sequence?
o A machine develops plans?
o A machine diagnoses and prescribes?
o A machine answers ambiguous questions?
o A machine recognizes fingerprints?
o A machine understands?
o A machine perceives?
o A machine does MANY MORE SUCH THINGS …
o A machine behaves as HUMANS do? HUMANOID!!!

12
 AI system Definition

1. Systems that THINK Like

Humans

2. Systems that ACT Like

Humans

13
 Systems that THINK Like
Humans
o “[The automation of activities that we
associate with human thinking, activities
such as decision making, problem
solving, learning …” (Bellman, 1978)

14
 Systems that THINK Like
Humans
o “The exciting new effort to make
computers think … machines with
minds, in the full and literal sense”
(Haugeland, 1985)

15
 Systems that THINK Like
Humans
o “The study of computation that make it
possible to perceive, reason and act”
(Winston 1992)

16
 Systems that THINK Like
Humans
o “The study of mental faculties through
the use of computational models”
(Charniak and McDermott)

17
 Systems that ACT Like
Humans
o “The art of creating machines that
perform functions that require
intelligence when performed by people”
(Kurzweil 1990)

18
 Systems that ACT Like
Humans
o “A field of study that seeks to explain
and emulate intelligent behavior in terms
of computational processes” (Schalkoff,
1990)

19
 Systems that ACT Like
Humans
o “The branch of computer science that is
concerned with the automation of
intelligent behavior” (Luger and
Stubblefield, 1993)

20
 Systems that ACT Like
Humans
o “The study of how to make computers
do things which, at the moment, people
do better” (Rich and Knight, 1991)
o On the face of it, this definition may
appear simplistic
o However, the term “at the moment” has
a significant time element

21
 What About the Brain?
 Brains (human minds) are very
good at making rational decisions,
but not perfect
 Brains aren’t as modular as
software, so hard to reverse
engineer!
 “Brains are to intelligence as
wings are to flight”
 Lessons learned from the brain:
memory and simulation are key to
decision making
22
 Designing Rational Agents
o An agent is an entity that
perceives and acts.
o A rational agent selects
actions that maximize its
(expected) utility.
o Characteristics of the Percepts

Environment
Sensors
percepts, environment,

Agent
and action space dictate ?
techniques for selecting Actuators
rational actions Actions
23
 AI
Machine
Learning
[learning decisions]

Robots Rational Human-AI

[physically Agents Interaction
embodied] [decisions]

NLP
Computer
Vision
24
 A (Short) History of AI
o 1940-1950: Early days
o 1943: McCulloch & Pitts: Boolean circuit model of brain
o 1950: Turing's “Computing Machinery and Intelligence”
o 1950—70: Excitement:
o 1950s: Early AI programs, including Samuel's checkers program, Newell & Simon's Logic
Theorist, Gelernter's Geometry Engine
o 1956: Dartmouth meeting: “Artificial Intelligence” adopted
o 1965: Robinson's complete algorithm for logical reasoning
o 1970—90: Knowledge-based approaches
o 1969—79: Early development of knowledge-based systems
o 1980—88: Expert systems industry booms
o 1988—93: Expert systems industry busts: “AI Winter”
o 1990—: Statistical approaches
o Resurgence of probability, focus on uncertainty
o General increase in technical depth
o Agents and learning systems… “AI Spring”?
25
 Natural Language
o Speech technologies (e.g. Siri)
o Automatic speech recognition (ASR)
o Text-to-speech synthesis (TTS)
o Dialog systems

o Language processing technologies

o Question answering
o Machine translation

o Web search
o Text classification, spam filtering, etc…
26
 Computer Vision

Karpathy & Fei-Fei, 2015; Donahue et al., 2015; Xu et al, 2015; many27
more
Tools for Predictions & Decisions

28
29
 Game Agents
o Classic Moment: May, '97: Deep Blue vs. Kasparov
oFirst match won against world champion
o“Intelligent creative” play
o200 million board positions per second

30
 Game Agents
o Reinforcement learning

31
 Simulated Agents

[Schulman, Moritz, Levine, Jordan, Abbeel, ICLR 2016] 32

 Robotics
o Vehicles
o Rescue
o Help in the home
o Lots of automation…

33