Fall 2009 CAP 6616 Neuroevolution and Generative and Developmental Systems: Syllabus
MW 11:30AM - 12:45PM in HEC room 103
Instructor: Dr. Kenneth Stanley
EPlex Research Group: http://eplex.cs.ucf.edu
Office: Harris 332
Office Hours (starting 8/24/09): Mondays 1-2pm and Tuesdays 3-4pm
TextsFundamentals of Neural Networks by Laurene V. Fausett (1994)
Evolutionary Computation: A Unified Approach by Kenneth A. De Jong (2006)
(Sometimes listed as 2002)
Assorted Current Research Papers
Software and Source CodeAny version of NEAT can be used in the class projects. A number of versions are available here: http://www.cs.ucf.edu/~kstanley/#software
The latest clean version written by myself is rtNEAT, available here. A stripped down version of my non-real-time code is neatVS.zip, refitted for easy compiling by Jared Johnson..
OverviewThe purpose of this artificial intelligence (AI) course is to introduce students to current topics in the artificial evolution of complex systems, focusing on evolving neural networks (i.e. neuroevolution). In neuroevolution, a Darwinian survival-of-the-fittest competition among neural networks leads to increasingly sophisticated solutions without the need for human design. However, such a process requires a principled approach to combining, selecting, and encoding large, complex neural networks. The class will also examine sophisticated encoding techniques based on the growth of an embryo from a single cell (i.e. generative and developmental systems) and DNA encoding in nature. Such techniques promise to facilitate the evolution of neural networks with orders of magnitude more complexity than has been heretofore possible. This course will introduce students to the cutting edge of such research, culminating in a project in which students program their own system that evolves increasingly complex structures over time. Neural networks are a good proxy for complex systems in general, exhibiting many of the key properties that make such systems difficult to evolve. The class surveys methods in neuroevolution that have resulted in new ways to produce controllers for a broad range of difficult sequential decision tasks and creative endeavors, including robot and autonomous vehicle control, pattern generation, limb coordination, warning systems, factory optimization, intelligent video games, and computer-generated art and music. Although neural networks are a major focus for the course, students will not be restricted in the type of structure their systems can evolve. In this way, students will become experts through hands-on experience.
Grading PolicyGrades will be based 65% on a final project (10% final presentation and 55% final report), 25% on project milestones, and 10% on quizes on assigned papers. Students must work with a partner and periodically report how they are allocating tasks.
Late policy: 20% off if turned in within one week. Otherwise, not accepted.
Project Milestones (25% of grade; all milestones must be turned in as a hardcopy report):
9/16: Initial proposal and project plan (5%)
9/28: XOR test (5%)
10/7: Domain code prelim (5%)
11/2: Midterm presentation and report (10%)
12/7: Final project and presentation (65% of grade)
CheatingAll of the work that you turn in or present must be your own. Cheating, plagiarism, and any other form of academic dishonesty will be penalized. The minimum penalty for cheating will include:
- An automatic zero on the assignment -- this grade may not be dropped; and
- reduction of your final grade by one letter grade; and
- notification of the incident to the UCF Office of Student Conduct.
Plagiarism and paraphrasing are forms of cheating. Plagiarism is the presentation of others' ideas and writings as your own. Paraphrasing is taking someone else's sentence, changing a few words, and then presenting it as your own. Both are unacceptable in this class.
ScheduleAugust 24 Intro, context within AI, Prior Projects
August 26 Neural Networks Basics, Sequential Decision Problems, Complexity and Search
August 31st NEAT, CPPNs, HyperNEAT, Novelty Search Overviews and Applications
September 2 Project Discussions
September 7 No Class: Labor Day
September 9 Topics in Neural Networks: Backprop, Hebbian Learning, Biological Inspirations, Reinforcement Learning
September 14 Topics in Evolutionary Computation: Types of EC, Genetic Algorithms Basics
September 16 Genetic Algorithms Theory, Criticisms of EC, No Free Lunch
Initial Proposal and Project Plan Due
September 21 Neuroevolution (Evolving Neural Networks): Combining EC with NNs, Significance to AI, Classic obstacles
September 23 History of Neuroevolution, TWEANNS
September 28 NeuroEvolution of Augmenting Topologies (NEAT): Overcoming the obstacles
XOR Test Due
September 30 Post-NEAT Methods and Working with NEAT
October 5 Generative and Developmental Systems: The Power of Reuse, Prior Work, Biological Underpinnings, Skeptical Perspective
October 7 Compositional Pattern Producing Networks (CPPNs)
Preliminary Domain Code Due
October 12 HyperNEAT: Hypercube-based NEAT
October 14 Abandoning Objectives and the Search for Novelty
October 19 Advanced HyperNEAT
October 21 Real-time NEAT and the NERO video game
October 26 Advanced implementation issues for ANNs in video games
October 28 Competitive Coevolution and Complexification
November 2 Midterm Project Reports
November 4 Midterm Project Reports
November 9 More realistic neural models: Adaptive synapses
November 11 No Class: Veteran's Day
November 16 More on realistic neurons: Leaky integrator neurons
November 18 Interactive Evolutionary Computation and Genetic Art (Art, music, and other applications)
November 23 Evolution as a creative process, target-based vs. non-target-based evolution, large-scale IEC, Picbreeder, the organization dividend and "oragnizational metamorphosis"
November 25 The Puzzle of Complexification in Indirectly-Represented Phenotypes
November 30 Closing Remarks; Implementation Topics and Discussion
December 2 Project Discussion
December 7 Final Presentations
Final Projects Due
Classes End December 7th
December 10 Final Presentations
Student Final Presentations: Students will have run their own experiments in neuroevolution and generative and developmental systems and will present results and methods from their projects.