Date post: | 17-Jan-2016 |
Category: |
Documents |
Upload: | clementine-blair |
View: | 216 times |
Download: | 0 times |
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Lecture 37 of 42
Monday, 01 December 2008
William H. Hsu
Department of Computing and Information Sciences, KSU
KSOL course page: http://snipurl.com/v9v3
Course web site: http://www.kddresearch.org/Courses/Fall-2008/CIS730
Instructor home page: http://www.cis.ksu.edu/~bhsu
Reading for Next Class:
Sections 22.1, 22.6-7, Russell & Norvig 2nd edition
Vision, Part 1 of 2Discussion: GEC Concluded
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Lecture Outline
This Week: Chapter 26, Russell and Norvig 2e
Today: Chapter 23, R&N 2e
Wednesday (Last Lecture!): Chapter 24, R&N 2e
References Robot Vision, B. K. P. Horn
Courses: http://www.palantir.swarthmore.edu/~maxwell/visionCourses.htm
UCB CS 280: http://www.cs.berkeley.edu/~efros/cs280/
The Vision Problem Early vs. late vision
Marr’s 2 ½ - D sketch
Waltz diagrams
Shape from Shading Ikeuchi-Horn method
Subproblems: edge detection, segmentation
Optical Flow
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
GP Flow Graph
Adapted from The Genetic Programming Notebook © 2002 Jaime J. Fernandezhttp://www.geneticprogramming.com
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Structural Crossover
Adapted from The Genetic Programming Notebook © 2002 Jaime J. Fernandezhttp://www.geneticprogramming.com
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Structural Mutation
Adapted from The Genetic Programming Notebook © 2002 Jaime J. Fernandezhttp://www.geneticprogramming.com
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Genetic Programming: The Next Generation
(Synopsis and Discussion) Automatically-Defined Functions (ADFs)
aka macros, anonymous inline functions, subroutines
Basic method of software reuse
Questions for Discussion
What are advantages, disadvantages of learning anonymous functions?
How are GP ADFs similar to and different from human-produced functions?
Exploiting Advantages
Reuse
Innovation
Mitigating Disadvantages
Potential lack of meaning – semantic clarity issue (and topic of debate)
Redundancy
Accelerated bloat – scalability issue
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Code Bloat [1]:Problem Definition
Definition Increase in program size not commensurate with increase in functionality
(possibly as function of problem size)
Compare: structural criteria for overfitting, overtraining
Scalability Issue Large GPs will have this problem
Discussion: When do we expect large GPs?
Machine learning: large, complex data sets
Optimization, control, decision making / DSS: complex problem
What Does It Look Like?
What Can We Do About It? ADFs
Advanced reuse techniques from software engineering: e.g., design patterns
Functional, object-oriented design; theory of types
Controlling size: parsimony (MDL-like), optimization (cf. compiler)
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Code Bloat [2]:Mitigants
Automatically Defined Functions
Types
Ensure
Compatibility of functions created
Soundness of functions themselves
Define: abstract data types (ADTs) – object-oriented programming
Behavioral subtyping – still “future work” in GP
Generics (cf. C++ templates)
Polymorphism
Advanced Reuse Techniques
Design patterns
Workflow models
Inheritance, reusable classes
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Code Bloat [3]:More Mitigants
Parsimony (cf. Minimum Description Length)
Penalize code bloat
Inverse fitness = loss + cost of code (evaluation)
May include terminals
Target Language Optimization
Rewriting of constants
Memoization
Loop unrolling
Loop-invariant code motion
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Genetic Programming 3(Synopsis and Discussion [1])
Automatic Program Synthesis by Computational Intelligence: Criteria
1. Specification: starts with what needs to be done
2. Procedural representation: tells us how to do it
3. Algorithm implementation: produces a computer program
4. Automatic determination of program size
5. Code reuse
6. Parametric reuse
7. Internal storage
8. Iteration (while / for), recursion
9. Self-organization of hierarchies
10. Automatic determination of architecture
11. Wide range of programming constructs
12. Well-defined
13. Problem independent
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Genetic Programming 3(Synopsis and Discussion [2])
16 Criteria for Automatic Program Synthesis …
14. Generalization: wide applicability
15. Scalability
16. Human-competitiveness
Current Bugbears: Generalization, Scalability
Discussion: Human Competitiveness?
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Summary of Videos
GP1: Basics of SGP
GP2: ADFs and Problem of Code Bloat
GP3: Advanced Topics
A. M. Turing’s 16 criteria
How GP does and does not (yet) meet them
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
More Food for Thoughtand Research Resources
Discussion: Future of GP
Current Applications
Conferences
GECCO: ICGA + ICEC + GP
GEC
EuroGP
Journals
Evolutionary Computation Journal (ECJ)
Genetic Programming and Evolvable Machines (GPEM)
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
More Food for Thoughtand Research Resources
Discussion: Future of GP
Current Applications
Conferences
GECCO: ICGA + ICEC + GP
GEC
EuroGP
Journals
Evolutionary Computation Journal (ECJ)
Genetic Programming and Evolvable Machines (GPEM)
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision)
Line Drawing Interpretation
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision)
Line Labeling [1]:Solid Polyhedra and Other Shapes
Waltz,others
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision)
Line Labeling [2]:Junctions
Junctions occur at tangent discontinuities
FalseT-junctions
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Adapted from slides © 1999 T. Leung, UC Berkeley (CS 280 Computer Vision)
Orientation and Texture Discrimination (Textons) [1]
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision)
Orientation and Texture Discrimination (Textons) [2]
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision)
Segmentation (Grouping) [1]:Definition
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision)
Segmentation (Grouping) [2]:Physical Factors
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision)
Edge Detection [1]:Convolutional Filters and Gaussian
Smoothing
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision)
Edge Detection [2]:Difference of Gaussian
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision)
Binocular Stereo [1]:Stereo Correspondence – Properties
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision)
Binocular Stereo [2]:Stereo Correspondence – Open Problems
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision)
Optical Flow
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Terminology
Vision Problem Early vs. late vision
Marr’s 2 ½ - D sketch
Waltz diagrams
Shape from Shading Ikeuchi-Horn method
Subproblems: edge detection, segmentation
Optical Flow
Computing & Information SciencesKansas State University
Monday, 01 Dec 2008CIS 530 / 730: Artificial Intelligence
Summary Points
References Robot Vision, B. K. P. Horn
http://www.palantir.swarthmore.edu/~maxwell/visionCourses.htm
The Vision Problem Early vs. late vision
Marr’s 2 ½ - D sketch
Waltz diagrams
Shape from Shading Ikeuchi-Horn method
Subproblems: edge detection, segmentation
Optical Flow
Next Week Natural Language Processing (NLP) survey
Final review