- author = "Andrew James Turner",
- title = "Evolving Artificial Neural Networks using Cartesian Genetic Programming",
- school = "Electronics, University of York",
- year = "2015",
- address = "UK",
- month = sep,
- keywords = "genetic algorithms, genetic programming, Cartesian Genetic Programming, ANN, Fibonacci sequence",
-
URL = "
http://etheses.whiterose.ac.uk/12035/1/thesis.pdf",
-
URL = "
http://etheses.whiterose.ac.uk/12035/",
- size = "336 pages",
-
abstract = "NeuroEvolution is the application of Evolutionary
Algorithms to the training of Artificial Neural
Networks. NeuroEvolution is thought to possess many
benefits over traditional training methods including:
the ability to train recurrent network structures, the
capability to adapt network topology, being able to
create heterogeneous networks of arbitrary transfer
functions, and allowing application to reinforcement as
well as supervised learning tasks. This thesis presents
a series of rigorous empirical investigations into many
of these perceived advantages of NeuroEvolution. In
this work it is demonstrated that the ability to
simultaneously adapt network topology along with
connection weights represents a significant advantage
of many NeuroEvolutionary methods. It is also
demonstrated that the ability to create heterogeneous
networks comprising a range of transfer functions
represents a further significant advantage. This thesis
also investigates many potential benefits and drawbacks
of NeuroEvolution which have been largely overlooked in
the literature. This includes the presence and role of
genetic redundancy in NeuroEvolution's search and
whether program bloat is a limitation.
The investigations presented focus on the use of a recently developed NeuroEvolution method based on Cartesian Genetic Programming. This thesis extends Cartesian Genetic Programming such that it can represent recurrent program structures allowing for the creation of recurrent Artificial Neural Networks. Using this newly developed extension, Recurrent Cartesian Genetic Programming, and its application to Artificial Neural Networks, are demonstrated to be extremely competitive in the domain of series forecasting",
