| Issue |
MATEC Web Conf.
Volume 76, 2016
20th International Conference on Circuits, Systems, Communications and Computers (CSCC 2016)
|
|
|---|---|---|
| Article Number | 04035 | |
| Number of page(s) | 4 | |
| Section | Computers | |
| DOI | https://doi.org/10.1051/matecconf/20167604035 | |
| Published online | 21 October 2016 | |
Adaptive individual handling for neural network synthesis
Tomas Bata University in Zlín, Faculty of Applied Informatic, nám. T. G. Masaryka 5555, 760 01 Zlín, Czech Republic
a Corresponding author: varacha@fai.utb.cz
Neural Network Synthesis is an algorithm capable of creating and learning and artificial neural networks as well as optimizing their structures and connections. The method is based on Analytic Programming and asynchronous implementation of Self-Organising Migration Algorithm. Such approach already recorded several successful application considering practical casers of modelling and simulation. This results vindicate efforts for its further development. This paper explores a possibility to make it more effective by adaptive individual handling. The main idea is an intelligent control the process based on complexity of processed neural network structure.
© 2016 The Authors. Published by Elsevier Ltd.
Peer-review under responsibility of DAAAM International Vienna.
Key words: neural / network / synthesys / SOMA / adaptive / strategy / structural / optimization
© The Authors, published by EDP Sciences, 2016
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.