Page 155 - 49A Field Guide to Genetic Programming

Chapter 14

Conclusions

In his seminal paper entitled “Intelligent Machinery”, Turing (1948) identi-
fied three ways by which human-competitive machine intelligence might be
achieved. In connection with one of those ways, Turing said:
There is the genetical or evolutionary search by which a com-
bination of genes is looked for, the criterion being the survival
value. (Turing, 1948)
Turing did not specify how to conduct the “genetical or evolutionary
search” for machine intelligence. In particular, he did not mention the idea of
a population-based parallel search in conjunction with sexual recombination
(crossover) as described in Holland’s 1975 book Adaptation in Natural and
Artificial Systems (Holland, 1992, second edition). However, in Turing’s
paper “Computing Machinery and Intelligence” (Turing, 1950), he did point
out:
We cannot expect to find a good child-machine at the first at-
tempt. One must experiment with teaching one such machine
and see how well it learns. One can then try another and see
if it is better or worse. There is an obvious connection between
this process and evolution:

‘Structure of the child machine’ = Hereditary material
‘Changes of the child machine’ = Mutations
‘Natural selection’ = Judgement of the experimenter
In other words, Turing perceived that one possibly productive approach
to machine intelligence would involve an evolutionary process in which a
description of a computer program (the hereditary material) undergoes pro-
gressive modification (mutation) under the guidance of natural selection
(that is, selective pressure in the form of what we now call “fitness”).

141