Exploring the Impact of Different Classification Quality Functions in an ACO Algorithm for Learning Neural Network Structures

Khalid M. Salama, Ashraf M. Abdelbar

Abstract

Although artificial neural networks can be a very effective classification method, one of the drawbacks of their use is the need to manually prescribe the neural network topology. Recent work has introduced the ANN-Miner algorithm, an Ant Colony Optimization (ACO) technique for optimizing the topology of arbitrary FFNN's, i.e. FFNN's with multiple hidden layers, layer-skipping connections, and without the requirement of full-connectivity between successive layers. In this paper, we explore the use of several classification quality evaluation functions in ANN-Miner. Our experimental results, using 30 popular benchmark datasets, identify several quality functions that significantly improve on the simple Accuracy quality function that was previously used in ANN-Miner.

References

  1. Boryczka, U. and Kozak, J. (2010). Ant colony decision trees. In 4th International Conference on Computational Collective Intelligence, pages 4373-382.
  2. Boryczka, U. and Kozak, J. (2011). An adaptive discretization in the ACDT algorithm for continuous attributes. In 3rd International Conference on Computational Collective Intelligence, pages 475-484.
  3. Dorigo, M. and St ├╝tzle, T. (2004). Ant Colony Optimization. MIT Press, Cambridge, MA, USA.
  4. Liao, T., Socha, K., de Oca, M. M., Stuetzle, T., and Dorigo, M. (2014). Ant colony optimization for mixed-variable optimization problems. To appear in IEEE Transactions on Evolutionary Computation.
  5. Otero, F., Freitas, A., and Johnson, C. (2009). Handling continuous attributes in ant colony classification algorithms. In IEEE Symposium on Computational Intelligence in Data Mining (CIDM-09), pages 225-231.
  6. Otero, F., Freitas, A., and Johnson, C. (2013). A new sequential covering strategy for inducing classification rules with ant colony algorithms. IEEE Transactions on Evolutionary Computation, 17(1):64-74.
  7. Otero, F. E. B., Freitas, A. A., and Johnson, C. G. (2012). Inducing decision trees with an ant colony Applied Soft Computing,
  8. Parpinelli, R. S., Lopes, H. S., and Freitas, A. A. (2002). Data mining with an ant colony optimization algorithm. IEEE Transactions on Evolutionary Computation, 6(4):321-332.
  9. Salama, K., Abdelbar, A., and Freitas, A. (2011). Multiple pheromone types and other extensions to the AntMiner classification rule discovery algorithm. Swarm Intelligence, 5(3-4):149-182.
  10. Salama, K., Abdelbar, A., Otero, F., and Freitas, A. (2013). Utilizing multiple pheromones in an ant-based algorithm for continuous-attribute classification rule discovery. Applied Soft Computing, 13(1):667-675.
  11. Salama, K. M. and Abdelbar, A. M. (2014). A novel ant colony algorithm for building neural network topologies. In Proceedings ANTS-14. Accepted.
  12. Socha, K. and Blum, C. (2007). An ant colony optimization algorithm for continuous optimization: Application to feed-forward neural network training. Neural Computing & Applications, 16:235-247.
  13. Socha, K. and Dorigo, M. (2008). Ant colony optimization for continuous domains. European Journal of Operational Research, 185:1155-1173.
Download


Paper Citation


in Bibtex Style

@conference{ecta14,
author={Khalid M. Salama and Ashraf M. Abdelbar},
title={Exploring the Impact of Different Classification Quality Functions in an ACO Algorithm for Learning Neural Network Structures},
booktitle={Proceedings of the International Conference on Evolutionary Computation Theory and Applications - Volume 1: ECTA, (IJCCI 2014)},
year={2014},
pages={137-144},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005031301370144},
isbn={978-989-758-052-9},
}


in Harvard Style

Salama K. and Abdelbar A. (2014). Exploring the Impact of Different Classification Quality Functions in an ACO Algorithm for Learning Neural Network Structures . In Proceedings of the International Conference on Evolutionary Computation Theory and Applications - Volume 1: ECTA, (IJCCI 2014) ISBN 978-989-758-052-9, pages 137-144. DOI: 10.5220/0005031301370144


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Evolutionary Computation Theory and Applications - Volume 1: ECTA, (IJCCI 2014)
TI - Exploring the Impact of Different Classification Quality Functions in an ACO Algorithm for Learning Neural Network Structures
SN - 978-989-758-052-9
AU - Salama K.
AU - Abdelbar A.
PY - 2014
SP - 137
EP - 144
DO - 10.5220/0005031301370144