Introduction 2018
Introduction 2018
Introduction 2018
for Engineers
EE 562
Autumn 2018
1
Administrative Details
• Instructor: Linda Shapiro, 634 CSE,
shapiro@cs.washington.edu
• TA: Dianqi Li, dianqili@uw.edu
• Course Home Page:
http://homes.cs.washington.edu/~shapiro/EE562
• Text: Artificial Intelligence: A Modern Approach (3rd edition),
Russell and Norvig
2
This Lecture
• What is AI all about, roughly from
Chapters 1 and 2.
• Begin looking at the Python language we
will use.
3
What is intelligence?
• What capabilities should a machine have
for us to call it intelligent?
4
Turing’s Test
• If the human cannot tell whether the
responses from the other side of a wall are
coming from a human or computer, then the
computer is intelligent.
5
Performance vs. Humanlike
• What is more important: how the program
performs or how well it mimics a human?
6
Mundane Tasks
• Perception
– Vision
– Speech
• Natural Language
– Understanding
– Generation
– Translation
• Reasoning
• Robot Control
7
Formal Tasks
• Games
– Chess
– Checkers
– Kalah, Othello
• Mathematics
– Logic
– Geometry
– Calculus
– Proving properties of programs
8
Expert Tasks
• Engineering
– Design
– Fault Finding
– Manufacturing planning
• Medical
– Diagnosis
– Medical Image Analysis
• Financial
– Stock market predictions
9
What is an intelligent agent?
• What is an agent?
• What does rational mean?
• Are humans always rational?
• Can a computer always do the right thing?
• What can we substitute for the right thing?
10
Intelligent Agents
• What kinds of agents already exist today?
11
Problem Solving
C
13
Constraint Satisfaction
Example: Map Coloring
14
Reasoning
• Given:
– x (human(x) -> animal(x))
– x (animal(x) -> (eats(x) drinks(x)))
• Prove:
– x (human(x) -> eats(x))
15
Learning
• Example: Neural Network
16
Natural Language Understanding
• Pick up a big red
block.
• OK.
• While hunting in
Africa, I shot an
elephant in my
pajamas.
• I don’t understand.
17
Computer Vision with Machine Learning
{trees, grass, cherry trees} {cheetah, trunk} {mountains, sky} {beach, sky, trees, water}
? ? ? ? 18
Groundtruth Data Set:
Annotation Samples
tree(97.3), sky(99.8),
bush(91.6), Columbia gorge(98.8),
spring flowers(90.3), lantern(94.2), street(89.2),
flower(84.4), house(85.8), bridge(80.8),
park(84.3), car(80.5), hill(78.3),
sidewalk(67.5), boat(73.1), pole(72.3),
grass(52.5), water(64.3), mountain(63.8),
pole(34.1) building(9.5)
24