|CLASS SCHEDULE |
|March 5: Lecture|
|March 12: Lecture|
|March 19: Lecture (until 12pm)|
|March 26: Lecture|
|April 2: Lecture|
|April 9: Lecture|
|April 16: Pesach|
|April 23: Presentations|
|April 30: MIDTERM + Presentations|
|May 7: Guest Lecture|
|May 14: Yom Hastudent|
|May 21: Presentations|
|May 28: Project|
|June 4: Shavuot|
|June 11: Project|
|June 18: Project|
202-2-5651, Semester Beit, 2013-2014
Professor Moshe Sipper
- April 23: Yarden P, Yuval Z, Oron A, Lior L, Roei L, Itay A, Nir H, Ben L, Ran K, Nimrod M
- April 30 (+3 bonus): Yuri S, Aviad H, Avi L, Tomer S, Noa L
- May 21: Michael S, Yogev L, Shira A, Lior O, Aviel H, Alexander T, Snir E, Samanta H, Avi I, Pavel V
- Yuri Shafet, EvoMCTS: Enhancing MCTS-Based Players through Genetic Programming
- Michael Schneider, UAV Intelligent Path Planning for Wilderness Search and Rescue
- Aviad Hadad, Scaling Genetic Algorithms Using MapReduce
- Noa Levy, Guarding Against Premature Convergence while Accelerating Evolutionary Search
- Aviel Hershkovitz, Generating War Game Strategies Using A Genetic Algorithm
- Alexander Thereshchuk, Evolving artificial neural networks
- Lior Landesman, On The Evolution of Corewar Warriors
- Tomer Shahar, Using Genetic Algorithms to Evolve Character Behaviors in Modern Video Games
- Lior Orenbach, Evolving Pac-Man Players: Can We Learn from Raw Input?
- Avi Levin, Multiagent Learning through Neuroevolution
- Snir Elkaras, Using genetic algorithms to optimise current and future health planning - the example of ambulance locations
- Ran Kopelman, A replica exchange Monte Carlo algorithm for protein folding in the HP model
- Samanta Hourmann, An Improved Adaptive Differential Evolution Algorithm with Population Adaptation
- Avi Itzhakov, Using Symmetry and Evolutionary Search to Minimize Sorting Networks
- Itay Azaria, GP-Gammon: Genetically programming backgammon player
- Shira Aviv, pEvoSAT: A Novel Permutation Based Genetic Algorithm for Solving the Boolean Satisfiability Problem
- Nir Hadassi, Evolving Computer Opponents to Play a Game of Poker
- Roei Lichter, Genetic Programming Produced Competitive Soccer Softbot Teams for RoboCup97
- Yarden Peleg, Genetic Programming in the Wild: Evolving Unrestricted Bytecode
- Oron Ashual, An Investigation into Tournament Poker Strategy using Evolutionary Algorithms
- Yuval Zilbershtein, A self-learning evolutionary chess program
- Pavel Vaks, A Simple Genetic Algorithm for Music Generation by means of Algorithmic Information Theory
- Yogev Levy, Evolutionary approaches to the generation of optimal error correcting codes
- Nimrod Milo, GAME: detecting cis-regulatory elements using a genetic algorithm
- Ben Laor, how effective are multiple populations in genetic programming
- Yuri Shafet, Tomer Shahar, Leonid Orenbach:
- Michael Schneider: Improving upon "UAV Intelligent Path Planning for Wilderness Search and Rescue"
- Nimrod Milo: Incorporating Genetic programming into mining RNA structural motifs
- Noa Levy, Yarden Peleg: 2048 game
- Pavel Vaks: Optimizing Blackjack strategy by a Genetic Algorithm
- Ben Laor, Itay Azaria: Image classification using EC
- Avi Levin, Aviad Hadad: Fighting Game AI Competition
- Ran Kopelman, Lior Landsman: Geometric spanners
- Alexander Thereshchuk, Yogev Levy: Wind Farm Layout Optimization Competition
- Nir Hadassi, Roei Lichter: 15-puzzle
- Avi Itzhakov, Shira Aviv: Tetravex puzzle
- Aviel Hershkovitz, Snir Elkaras, Samanta Hourmann: Generating war game strategies using a genetic algorithm
- Yuval Zilbershtein, Oron Ashual: Warlight AI Challenge
- Prerequisites (for undergraduates):
- Credits: 4
- Time & Place: Wednesday, 10-14, 34/7
- Attendance is obligatory
(נוכחות חובה בכל השיעורים).
Attendance means: 1. being in class, and 2. arriving on time.
One unjustified absence: 2 points off final grade. Two unjustified absences: 5 points off final grade. Three or more unjustified absences: final grade is ZERO. Justified absence is one of those appearing in Section 7.2 here; any other absence is UNJUSTIFIED.
- 29%: Midterm
- 31%: Presentation
- 40%: Project
- You must pass the midterm in order to pass the course.
- If you miss the midterm
due to a valid reason according to the university regulations
(see Section 7.2),
then your grade will be calculated according to: Project (50%) and Presentation (50%).
- If you miss the midterm due to an invalid reason then the midterm's grade will count as 0.
- Sample midterm questions.
- Each student will present on his own a paper(s) from the research literature.
- You must select a topic by April 2. Timeslots will be assigned by lecturer.
- Presentation length: 18--20 minutes + 2 minutes Q&A.
- Scoring rubric: Organization (1-6), Knowledge (1-6), Text (1-6), Graphics (1-5), Elocution (1-5), Eye Contact (1-3).
- The project must be done in pairs or threesomes.
- The project report must be submitted by the end of the semester (June 20th)
- The project report must include the following seven sections:
- A short introduction of the domain being investigated.
- A description of the problem or phenomenon studied.
- An explanation of the methods and algorithms employed.
- An overview of the software (NOT a listing of the code).
- An account of the results obtained.
- Some interesting conclusions.
- Bibliographic references.
- Language: Hebrew or English.
- Length: 10-20 pages.
- Don't include the code in the report.
- Don't send the report by e-mail: hand in a hard copy.
- An example of a good report.
- Introduction to Evolutionary Computation
- What is an Evolutionary Algorithm?
- Genetic Algorithms
- GA Theory:
Holland's Schema Theorem,
Exact Schema Theorem
- Local Search Algorithms
- Working with Evolutionary Algorithms
- Introduction to Genetic Programming:
What is GP? (Koza's vid),
GP (Eiben & Smith),
GP Tutorial (Koza),
GP Tutorial (Koza & Poli)
- Evolution of Emergent Cooperative Behavior
- Koza's vids
- GP Theory: Poli's Tutorial (see
Field Guide, Ch. 11)
- Game Playing: Adversarial Search
- Evolving Game-Playing Strategies:
Attaining Human-Competitive Game-Playing with GP,
GP-Rush & GP-FreeCell,
- Darwinian Software Engineering
- Varieties of GP
- Architecture-Altering Operations
- Coevolving Sorting Networks
- Competitive Coevolution
- Coevolving Solutions to the SCS Problem
- Parameter Control
- Evolution Strategies
- M. Sipper, Evolved to Win, Lulu, 2011. (freely downloadable)
- M. Sipper,
Machine Nature: The Coming Age of Bio-Inspired Computing,
McGraw-Hill, New York, 2002.
- A.E. Eiben and J.E. Smith, Introduction to Evolutionary Computing, Springer, 1st edition, 2003, Corr. 2nd printing, 2007.
- R. Poli, B. Langdon, & N. McPhee, A Field Guide to Genetic Programming, 2008. (freely downloadable)
- J. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection, MIT Press, Cambridge, MA, 1992.
- S. Luke, Essentials of Metaheuristics, 2010. (freely downloadable)
- Z. Michalewicz & D.B. Fogel,
How to Solve It: Modern Heuristics, 2nd ed. Revised and Extended, 2004.
- Z. Michalewicz. Genetic Algorithms + Data Structures = Evolution Programs. Springer-Verlag, Berlin, 3rd edition, 1996.
- D. Floreano & C. Mattiussi,
Bio-Inspired Artificial Intelligence:
Theories, Methods, and Technologies, MIT Press, 2008.
- A. Tettamanzi & M. Tomassini,
Soft Computing: Integrating Evolutionary, Neural, and Fuzzy Systems,
Springer-Verlag, Heidelberg, 2001.