Amazon.co.uk, Amazon.com, and Amazon.de review:
neural networks and genetical search, 3 May, 2002
from Auckland, New Zealand.
A programmable digital computer, based on Alan Turing's design,
ran its first program in 1950 at the National Physical Laboratory,
London. Even today, every computer in the world remains
computationally equivalent to a Turing Machine. It is little known
however, that Turing also investigated neural network architectures as
early as 1948, and before the term genetic algorithm was coined,
proposed configuring his networks with a "genetical search". In this
book Teuscher presents the most extensive exploration of Turing's
neural networks available. The book contains over 100 diagrams,
detailed examinations of the logical behaviour of Turing's networks,
experiments into their emergent properties and extensions of Turing's
ideas based on recent findings. An understanding of Turing's networks
allows insight into a number of modern research areas such as
Kauffman's work on the principles of self-organisation, the boundaries
of computability, and even the real neural networks of living things
(Turing claimed that his neural networks were probably the simplest
possible model of the human cortex). Because the discussion in the
book starts with Turing's early networks and progresses through to
current research, it can also be read as an accessible overview of the
history of the field. In addition, the book makes it clear that there
are many interesting research questions still to be answered in this
area. As such, this book will be of interest to historians of computer
science and modern researchers alike.
Barbara Fournier, "Dans le cerveau d'un Oscar Wilde de
l'informatique", Polyrama, (116):10-11, 2002. English
translation available here.
"This is a fascinating book, full of instructive diagrams and
figures. It starts where Turing left off and covers many of the things
Turing would have loved to have done, if only he had had the computing
power. I found Teuscher's use of genetic algorithms particularly
interesting. I am sure Turing, and anyone interested in his work,
would enjoy reading this book."
Auckland University School of Medicine and Green Lane Hospital
Auckland, New Zealand
"I guess the world would have been a very different place
if `On Computable Numbers' had been called `a schoolboy essay' instead!"
Director, Cyberlife Research Ltd.
Hon. Research Fellow, PSYCH, Univ. of Cardiff
"So far as we know, after half a century Christof
Teuscher is the first to carry out a detailed exploration of Turing Nets."
B. Jack Copeland
The Turing Archive for the History of Computing
University of Canterbury, New Zealand