Lambert Schomaker

30
Lambert Schomaker KI2 - 2 Kunstmatige Intelligentie / RuG

description

KI2 - 2. Lambert Schomaker. Kunstmatige Intelligentie / RuG. Outline. Knowledge-based symbolic methods. Assumption: the Turing / Von Neumann computer is a universal computation engine… …therefore it can be used at all levels of information processing: - PowerPoint PPT Presentation

Transcript of Lambert Schomaker

Page 1: Lambert Schomaker

Lambert Schomaker

KI2 - 2

Kunstmatige Intelligentie / RuG

Page 2: Lambert Schomaker

2

Outline

Date 1st hour 2nd hour

6 nov Planning, N&R #11-13

(LS)

idem

13 nov Knowledge-based symbolic methods (LS) #19.6, #21

Example: geometric modeling & matching (MB)

20 nov Statistical symbolic

methods 1 (LS) #17

Example: spam filter

27 nov Statistical symbolic

methods 2 (LS)

Example: autoclass

4 dec Heterogeneous-information integration

Example: writer identification, sat. images

11 dec Grammar induction Articles

18 dec Misc. topics Misc. applications

jan (exam)

Page 3: Lambert Schomaker

3

Knowledge-based symbolic methods

Assumption: the Turing / Von Neumann computer is a universal computation engine…

…therefore it can be used at all levels of information processing:

provided an appropriate algorithm can be designed which operates on appropriate representations

Page 4: Lambert Schomaker

4

Knowledge-based symbolic methods

provided an appropriate algorithm can be designed…

which operates on appropriate representations…

Page 5: Lambert Schomaker

5

Knowledge-based symbolic methods

…provided an appropriate algorithm can be designed…

mechanisms: recursion, hierarchic procedures search algorithms parsers matching algorithms string manipulation.. numerical computing

signal processing image processing statistical processing

Page 6: Lambert Schomaker

6

Knowledge-based symbolic methods

…which operates on appropriate representations…

stacks linear strings and arrays matrices linked lists trees

Page 7: Lambert Schomaker

7

Knowledge-based symbolic methods

…which operates on appropriate representations…

stacks linear strings and arrays matrices linked lists trees

is indeed succesful in many information processing problems

Page 8: Lambert Schomaker

Example: double spiral problem

in inner orouter spiral?

Page 9: Lambert Schomaker

Example: double spiral problem

in inner orouter spiral?

difficult for, e.g., neural nets

Page 10: Lambert Schomaker

Example: double spiral problem

in inner orouter spiral?

Answer: outside

difficult for, e.g., neural nets

Page 11: Lambert Schomaker

Example: double spiral problem

in inner orouter spiral?

How?-flood fill algorithm?-other?

Page 12: Lambert Schomaker

Example: double spiral problem

in inner orouter spiral?

-Find the right representation!

odd/even count

is not sensitive to shape variations of the spiral: a general solution

= Outside

count edges

Page 13: Lambert Schomaker

Example: double spiral problem

in inner orouter spiral?

Outside

Page 14: Lambert Schomaker

14

Culture

If it doesn’t work, you didn’t think hard enough

You have to know what you do

You have to prove that & why it works

Even neural networks work on top of the Turing/von Neumann engine (it will always win)

If you’re smart, you can often avoid NP-completeness

Use of probabilities is a sign of weakness

Page 15: Lambert Schomaker

15

Strong points

Scalability is often possible Convenience: little context dependence, no

training Reusability Transformability (compilation) Algorithmic refinement once it is known

how to do a trick (e.g., graphics cards and

DSPs in mobile phones: ugly code but

highly efficient)

Page 16: Lambert Schomaker

16

Challenges

Knowledge dependence is expensive– not a problem in “IT” application design– a challenge to AI

Uncertainty

Noise

Brittleness

Page 17: Lambert Schomaker

17

Solutions

More and more representational weight: (UML, Semantic Web, XML solves everything)

Symbolic learning mechanisms:– induction: version spaces grammar inference– decision tree learning– rewriting formalisms

Active hypothesis testing (what if…, assume X…)

Page 18: Lambert Schomaker

18

Example

In Reading Systems (optical character recognition), only a small part of the algorithm concerns problems of image processing and character classification

Most of the code is concerned with the structure

of the text image:– where are the blobs? – are these blobs text, photo or graphics?– how to segment into meaningful chunks: characters, words?– what is the logical organization (reading order) in the physical

organization of pixels?

Knowledge-based approaches are a necessity!

Page 19: Lambert Schomaker
Page 20: Lambert Schomaker
Page 21: Lambert Schomaker
Page 22: Lambert Schomaker

Name of conference

Programme committee

Brief description of conference

Submission details

Page 23: Lambert Schomaker

23

Example of layout analysis

Knowing the type of a text block strongly reduces the number of possible interpretations

Example: “address block”

Address:– name of person– street, number– postal code, city

Page 24: Lambert Schomaker

prof dr. L.R.B. SchomakerGrote Appelstraat 239712 TS GroningenNederland

Amsterdam7/7/2003

Page 25: Lambert Schomaker

address

prof dr. L.R.B. SchomakerGrote Appelstraat 239712 TS GroningenNederland

Page 26: Lambert Schomaker

address

person name

street

codes+city

country

prof dr. L.R.B. SchomakerGrote Appelstraat 239712 TS GroningenNederland

Page 27: Lambert Schomaker

address

titles initials surname

street street ,,, digits

4 digits 2 upper case city name

country name

prof dr. L.R.B. SchomakerGrote Appelstraat 239712 TS GroningenNederland

Page 28: Lambert Schomaker

<address> <person> <title></title> <initials or first name> </initials or first name> <surname></surname> </person> <home> <street name></street name> <number> </number> </home> <city> <postal code> <four digits></four digits> <white space></white space> <two upper-case letters> …. </postal code> </city> <country> </country></address>

(address (title is-left-of initials is-left-of surname) is-above (street name is-left-of number) is-above (city)is-above (country))

Content Layout

prof dr. L.R.B. SchomakerGrote Appelstraat 239712 TS GroningenNederland

etc.

etc.

Page 29: Lambert Schomaker

<address> <person> <title></title> <initials or first name> </initials or first name> <surname></surname> </person> <home> <street name></street name> <number> </number> </home> <city> <postal code> <four digits></four digits> <white space></white space> <two upper-case letters> …. </postal code> </city> <country> </country></address>

(address (title is-left-of initials is-left-of surname) is-above (street name is-left-of number) is-above (city)is-above (country))

Content Layout

prof dr. L.R.B. SchomakerGrote Appelstraat 239712 TS GroningenNederland

etc.

etc.

HELPS TEXT CLASSIFICATION

HELPS TEXT SEGMENTATION

Page 30: Lambert Schomaker