Learning, generalisation, and functional entropy in random automata networks
by Alireza Goudarzi; Christof Teuscher; Natali Gulbahce; Thimo Rohlf
International Journal of Autonomous and Adaptive Communications Systems (IJAACS), Vol. 7, No. 3, 2014

Abstract: It has been shown (Van den Broeck and Kawai, 1990; Patarnello and Carnevali, 1987) that feedforward Boolean networks can learn to perform specific simple tasks and generalise well if only a subset of the learning examples is provided for learning. Here, we extend this body of work and show experimentally that random Boolean networks (RBNs), where both the interconnections and the Boolean transfer functions are chosen at random initially, can be evolved by using a state-topology evolution to solve simple tasks. We measure the learning and generalisation performance, investigate the influence of the average node connectivity K, the system size N, and introduce a new measure that allows to better describe the network's learning and generalisation behaviour. We show that the connectivity of the maximum entropy networks scales as a power-law of the system size N. Our results show that networks with higher average connectivity K (supercritical) achieve higher memorisation and partial generalisation. However, near critical connectivity, the networks show a higher perfect generalisation on the even-odd task.

Online publication date: Wed, 29-Oct-2014

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Autonomous and Adaptive Communications Systems (IJAACS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com