To understand the importance of this book, and the cutting-edge nature of its 19 technical reports, I ask you to contemplate the following analogy: Archeologists have uncovered a great ancient archive from a previously unknown civilization. The archive contains a large number of perfectly preserved copies of hundreds of thousands of manuscripts. Each manuscript has a beautiful better-than-photographic-quality illustration on the cover, and contains about eight to 100 “scripts.” These scripts seem to be in some intermediate language between pictograms and phonetics. Image analysis programs tell us that each script has billions of almost linearly interconnected micro-brush strokes (hence the name Poly-Meta-Ziga-Eese). The good news is that there are only four kinds of micro-brush strokes, and these are found in only four of the possible 16 combinations. Presuming that the scripts correspond to the accompanying illustrations, the archives have been sent to a team of cryptography experts, assuming this is a language and it must be easy to decode because of the illustrations, which tell us what the scripts describe.

To translate the analogy: geneticists have uncovered the archive of life, which is a correspondence between small sets (chromosome collections) of limited 4-tuple (amino-acid) DNA strands and the perfectly embodied living organisms that they describe. Since a real-world physical DNA strand (if it were unwound and stretched out) is generally longer than a meter, the cryptography experts (who try to understand the molecular genetic data) are looking at a very intractable, super-large, nondeterministic polynomial time (NP) complete problem, at least. Accordingly, one can think about this book as the court testimony of 19 international expert-witness teams--in the present installment of the greatest ongoing mystery in the history of unfolding science.

On the one hand, the cryptography experts are having an unusually difficult struggle in trying to crack the DNA-coded organism messages; but on the other, they are in the process of taking rich mathematical paradigms (which have not provided the expected breakthrough in the genetics arena) and applying them to less-complex puzzles, such as the stock market, optics, circuits, antenna space, or medical physiology data streams. Even though the genomics bioinformatics problem isn’t solved, one can readily appreciate the enormous economic value of real-world application spin-offs. This means that every cutting-edge researcher, in every computational discipline, working on any real-world application, should make it a point to keep abreast of the ongoing progress of genetic programming theory and practice, which is currently available in this book.

Turning now to the actual content of this volume, we find case studies on large data sets, where various abstract quantitative tests are applied to uncover embedded metrics, structures, and relationships, therein running the gamut to higher dimensionalities and to potentially exotic topologies. Of course, most of the book focuses on working with genome bioinformatics data series, within which the four major areas are inxrobotics, bioinformatics, symbolic regression, and design, but this too may be subject to change. In addition, there is much scattered discussion about hot design themes in this field, including: “native representation sufficiency for evolutionary techniques, simulatable and reasonable evolved solutions, genetic programming (GP) focusing on solutions with few operative parts, and GP creating novel designs.” There are novel variants of Markov chains, probability cases, phase transition models, filter design strategies, coevolving fitness, classifying, and sequencing, but these are just the typical reference markers in this volume of ongoing perturbations to ordinary hyper-adiabatic cognitive-transition space.

One more observation (from the vantage of a historian of science): it is easy to contemplate the various amorphous explorations of the prescientific researcher, while the structure of the scientific method seems common knowledge. Now, we are looking at glimpses of a postscientific framework, where it is virtually impossible to posit a coherent hypothesis, the heavy computational tools and tests brought to investigate these super large data sets are conceptually vague at this scale, and the results are novel by definition (because, being cutting edge, this multi-multi-million man-year tool has probably never been applied to another data set). Consequently, understanding the results is a matter of incomplete, albeit lengthy, interpretation. Accordingly, there is a great win-win synergy opportunity here for less-cutting-edge researchers to try these maturing tools on more intuitive data masses; they should be more able to appreciate the results, and the genetic programming cryptography community might then learn something new about how to interpret post-scientific results.

Finally, I was surprised by one remark in the book, that many in the genetic programming community see some “large-scale real-world problems” as being larger than the genome bioinformatics problems, a conjecture that disturbs my meditations. I suppose that I will have to wait for episode V in this continuing saga, since there is no way to sneak a peek into the future to find out the solution to the genetic programming mystery.