23
CAP6938 Neuroevolution and Developmental Encoding Non-Neural NEAT and Closing Remarks Dr. Kenneth Stanley October 30, 2006

CAP6938 Neuroevolution and Developmental Encoding Non-Neural NEAT and Closing Remarks

  • Upload
    agrata

  • View
    46

  • Download
    0

Embed Size (px)

DESCRIPTION

CAP6938 Neuroevolution and Developmental Encoding Non-Neural NEAT and Closing Remarks. Dr. Kenneth Stanley October 30, 2006. Outline. Complexification is a general concept Protecting innovation is a general concept Therefore, they can apply to anything without a defined dimensionality - PowerPoint PPT Presentation

Citation preview

Page 1: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

CAP6938Neuroevolution and Developmental Encoding

Non-Neural NEAT andClosing Remarks

Dr. Kenneth Stanley

October 30, 2006

Page 2: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Outline

• Complexification is a general concept

• Protecting innovation is a general concept

• Therefore, they can apply to anything without a defined dimensionality

• Example: Cellular Automata

Page 3: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Complexification is a General Concept

• Solving a smaller version of a problem and expanding the solution

• Making a rough estimate and refining it

• Building a structure piece by piece

• Elaboration of a pre-existing concept

Page 4: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Complexification Does Not Mean Optimizing Random Dimensions

From a Set• Example: 10-dimensional search space

• Now hold d2 through d10 constant and search d1 • Once you get a good value for d1, start

searching both d1 and d2 together, and so on• This is not complexification

– It is a naïve search assuming independent variables– Subject to simple deception– Usually won’t work

10987654321 ,,,,,,,,, dddddddddd

Page 5: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Then What Does it Mean?• Complexification means increasing information

about the solution– (Optimizing d1 does not increase general information

about the solution)• Initial dimensions are a complete solution on

their own (nothing is held at zero)• Complexification means finding the

dimensionality of the solution is part of the problem

• A neural network can have any number of weight dimensions and solve the same problem

• Most “dimensions” outside the current structure have no meaning on their own

Page 6: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Example

• 3 dimensions• Is dimension 2372 held at zero?• What exactly is dimension 2372?

– It depends on how the other 2371 dimensions turn out to relate to each other

– It is undefined; it doesn’t exist: • Not like d10 in prior example, which always exists

• Complexification is searching infinite undefined dimensions, or rather, it is not performing search in the usual sense. It is increasing information.

1

23

Page 7: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Example 2

• Problem: Find an expression of this function• Complexification says start with a very low

dimensional approximation as accurate as possible in its space

• Red line: 2-dimensional estimate y=mx+b– Now we could add new terms and refine the estimate– Analogous to bending the line like a rubber band for

each new dimension added– New estimate does not necessarily need exactly the

same term “mx+b”

x

y

Page 8: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Protecting Innovation is a General Concept

• New ideas need time to mature

• Children need time to grow up

• Ph.D. students need room to make mistakes

• Bigger often means slower, but not stupider

• Einstein was not the teacher’s pet– The long run is what matters– If we kicked him out early, we’d all lose

Page 9: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Speciation Protects Innovation

• An “idea” is represented as a niche

• The niche is a local, protected competition

• One niche does not directly compete with another

• Only the absolute worst are purged after sufficient opportunity is spent

Page 10: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

General Concepts Means They Don’t Have to Apply to a Neural Network

• Complexification and protection of innovation go hand in hand

• In order to elaborate, one must protect potential elaborations

• In order to grow one must have room

Page 11: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Novel Phenotype: Cellular Automata

• Set of pixels that change over time according to neighborhood rules

• The Game of Life is a familiar example of 2D cellular automata

From: http://www.bitstorm.org/gameoflife/

Page 12: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

2D Cellular Automata

• Pixels are in a line instead of a plane

• Change over time can be represented as a vertical graph:

time

From: Melanie Mitchell, James P. Crutchfield, and Rajarshi Das, "Evolving Cellular Automata with Genetic Algorithms: A Review of Recent Work", In Proceedings of the First International Conference on Evolutionary Computation and Its Applications (EvCA'96), Russian Academy of Sciences (1996).

Page 13: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Neighborhood Rules

• Next state for pixel determined by pixels in its neighborhood within some radius:

From: Melanie Mitchell, James P. Crutchfield, and Rajarshi Das, "Evolving Cellular Automata with Genetic Algorithms: A Review of Recent Work", In Proceedings of the First International Conference on Evolutionary Computation and Its Applications (EvCA'96), Russian Academy of Sciences (1996).

2(2r+1) bits per rule table

Page 14: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Can It Do Anything Useful?

• Maybe it can compute functions

• Popular task: Fill the line with whichever color is in the majority (Density Classification)

• Successful attempts: (r=3; 128 bits/genome)

Page 15: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Assessing Performance

• Measure % correct over unbiased distribution of many initial conditions

• Best performance is 86% on 149 pixels with r=3 (Juillé and Pollack 1998) using coevolution of rules and initial conditions

• Could we do a lot better than 86%?

• Maybe with complexification

Page 16: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Complexifying Cellular Automata

• How?

Page 17: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Complexifying Cellular Automata

• How? Expand the neighborhood

• Neighborhood doesn’t need to be symmetric or even contiguous

• Is this really complexification?– Yes: Unexpressed dimensions are undefined without knowing all

the dimensions– The initial rules give us only a little information, but good

information– The dimensions of the search space are the bits of the rule, not

the neighborhood positions– The rule includes the neighborhood positions, i.e. there is

structure. Position is a historical marker in this case.

00

000

11

010

101

110

Page 18: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Even More Abstract Complexification Solution

• A very wide neighborhood could be input into a neural network that computes a function of those inputs and outputs the next value for the bit in the middle

• The network that computes the function can complexify

…… …

Evolved Topology

Page 19: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Conclusion

• Complexification and protection of innovation may allow more complex and therefore powerful neighborhood functions to evolve (maybe beat 86% by using with coevolution?)

• Complexification and protection of innovation may allow far more complex solutions to anything

Page 20: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

NE & DE: What Have We Learned

• Search is not just optimization• Expanding complexity over generations is a powerful

idea• Protecting innovation is as well• Neural networks can be grown with this method• The mapping between genotype and phenotype is

equally important: – Reuse of genes is powerful

• The neural model can be enhanced in several ways• NEAT can evolve any kind of structure, including

DE/indirect encodings, and CPPNs

Page 21: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

What Is Its Significance?• These are the forces of nature• We are unlocking nature’s box by

understanding the underlying algorithms• Much of the beauty and complexity of

nature, and civilization itself, resulted from these simple processes

• Biological evolution was an unguided process

• What will we create if we take its reigns and guide it?

Page 22: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Where is the Field?

• Two parallel streams1) How to evolve with complexification

2) How to represent with reuse (DE)

• More progress so far on 1 than 2– Indirect encoding is on the brink

• The two streams are merging (e.g. CPPNs)• A complexifying system with an efficient

encoding (mapping) is the next generation system

Page 23: CAP6938 Neuroevolution and Developmental Encoding  Non-Neural NEAT and Closing Remarks

Next Topics:Technical topics in implementing

complexifying evolutionary systems and presenting results.

• Practical implementation issues• Questions and group discussion/problem solving• How to present research results

Reference: Section 3 of Real-time Neuroevolution in the NERO Video Game by Stanley, Bryant, and Miikkulainen (2005). (Has most up-to-date NEAT description)