The Entry for 2013 HUMIES

1. the complete title of one (or more) paper(s) published in the open literature describing the work that the author claims describes a human-competitive result,

"Reusing Building Blocks of Extracted Knowledge to Solve Complex, Large-Scale Boolean Problems"

2. the name, complete physical mailing address, e-mail address, and phone number of EACH author of EACH paper,

		Muhammad Iqbal
		School of Engineering and Computer Science
		Victoria University of Wellington
		New Zealand
		muhammad.iqbal@ecs.vuw.ac.nz
		+64 4 463 5233 x7548

		Will N. Browne
		School of Engineering and Computer Science
		Victoria University of Wellington
		New Zealand
		will.browne@ecs.vuw.ac.nz
		+64 4 463 5233 x8489

		Mengjie Zhang
		School of Engineering and Computer Science
		Victoria University of Wellington
		New Zealand
		mengjie.zhang@ecs.vuw.ac.nz
		+64 4 463 5654

3. the name of the corresponding author (i.e., the author to whom notices will be sent concerning the competition),

		Muhammad Iqbal

4. the abstract of the paper(s),

"Evolutionary computation techniques have had limited capabilities in solving large-scale problems due to the large search space demanding large memory and much longer training times. In the work presented here, a genetic programming like rich encoding scheme has been constructed to identify building blocks of knowledge in a learning classifier system. The fitter building blocks from the learning system trained against smaller problems have been utilized in a higher complexity problem in the domain in order to achieve scalable learning. The proposed system has been examined and evaluated on four different Boolean problem domains, i.e. multiplexer, majority-on, carry, and even-parity problems. The major contribution of this work is to successfully extract useful building blocks from smaller problems and reuse them to learn more complex, large-scale problems in the domain, e.g. 135-bits multiplexer problem, where the number of possible instances is 2135 4 × 1040, is solved by reusing the extracted knowledge from the learnt lower level solutions in the domain. Autonomous scaling is, for the first time, shown to be possible in learning classifier systems.
It improves effectiveness and reduces the number of training instances required in large problems, but requires more time due to its sequential build-up of knowledge."

5. a list containing one or more of the eight letters (A, B, C, D, E, F, G, or H) that correspond to the criteria that the author claims that the work satisfies,

		G

6. a statement stating why the result satisfies the criteria that the contestant claims,

Human beings have the ability to apply the domain knowledge learned from smaller problems to more complex problems of the same or a related domain, but currently the vast majority of evolutionary computation techniques lack this ability. This lack of ability to apply the already learned knowledge of a domain results in consuming more resources and time to solve complex, large-scale problems of the domain. As the problem scales, it becomes difficult and even sometimes impractical (if not impossible) to solve due to the needed resources and time. 

We have developed a transfer learning based classifier system that successfully extracts useful building blocks (in the form of genetic programming-tree like code-fragments) from smaller problems and reuses them to learn more complex, large-scale problems in the domain. The developed system, known as XCSCFC, readily solves problems of a scale that existing learning classifier system and genetic programming approaches cannot, e.g. the 135-bits MUX problem.

Referring to the eight criteria for establishing that an automatically created result is competitive with a human-produced result, the XCSCFC system satisfies the following criteria:

(G) The result solves a problem of indisputable difficulty in its field. 

7. a full citation of the paper (that is, author names; publication date; name of journal, conference, technical report, thesis, book, or book chapter; name of editors, if applicable, of the journal or 	edited book; publisher name; publisher city; page numbers, if applicable);

Muhammad Iqbal, Will Browne, Mengjie Zhang. "Reusing Building Blocks of Extracted Knowledge to Solve Complex, Large-Scale Boolean Problems". IEEE Transactions on Evolutionary Computation. (Accepted on Jun 2, 2013) 

8. a statement either that "any prize money, if any, is to be divided equally among the co-authors" OR a specific percentage breakdown as to how the prize money, if any, is to be divided among the co-authors; and

"Any prize money, if any, is to be divided equally among the co-authors".

9. a statement stating why the judges should consider the entry as "best" in comparison to other entries that may also be "human-competitive". 

The XCSCFC system is the first that autonomously identifies building blocks of information to reuse in a cooperative rule-based system that can scale to solve previously not-learnable problems in the field of evolutionary computation as well as in the field of artificial transfer learning systems. It is anticipated that XCSCFC will be used as a strong base for more powerful lifelong learning artificial systems.