Portuguese Conference on Artificial Intelligence

EPIA 2015: Progress in Artificial Intelligence pp 280-285 | Cite as

Semantic Learning Machine: A Feedforward Neural Network Construction Algorithm Inspired by Geometric Semantic Genetic Programming

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9273)


Geometric Semantic Genetic Programming (GSGP) is a recently proposed form of Genetic Programming in which the fitness landscape seen by its variation operators is unimodal with a linear slope by construction and, consequently, easy to search. This is valid across all supervised learning problems. In this paper we propose a feedforward Neural Network construction algorithm derived from GSGP. This algorithm shares the same fitness landscape as GSGP, which allows an efficient search to be performed on the space of feedforward Neural Networks, without the need to use backpropagation. Experiments are conducted on real-life multidimensional symbolic regression datasets and results show that the proposed algorithm is able to surpass GSGP, with statistical significance, in terms of learning the training data. In terms of generalization, results are similar to GSGP.


Toxicity Eter 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Archetti, F., Lanzeni, S., Messina, E., Vanneschi, L.: Genetic programming for computational pharmacokinetics in drug discovery and development. Genetic Programming and Evolvable Machines 8(4), 413–432 (2007)CrossRefGoogle Scholar
  2. 2.
    Gonçalves, I., Silva, S.: Balancing learning and overfitting in genetic programming with interleaved sampling of training data. In: Krawiec, K., Moraglio, A., Hu, T., Etaner-Uyar, A.Ş., Hu, B. (eds.) EuroGP 2013. LNCS, vol. 7831, pp. 73–84. Springer, Heidelberg (2013) CrossRefGoogle Scholar
  3. 3.
    Gonçalves, I., Silva, S., Fonseca, C.M.: On the generalization ability of geometric semantic genetic programming. In: Machado, P., Heywood, M.I., McDermott, J., Castelli, M., García-Sánchez, P., Burelli, P., Risi, S., Sim, K. (eds.) Genetic Programming. LNCS, vol. 9025, pp. 41–52. Springer, Heidelberg (2015)Google Scholar
  4. 4.
    Gonçalves, I., Silva, S., Melo, J.B., Carreiras, J.M.B.: Random sampling technique for overfitting control in genetic programming. In: Moraglio, A., Silva, S., Krawiec, K., Machado, P., Cotta, C. (eds.) EuroGP 2012. LNCS, vol. 7244, pp. 218–229. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  5. 5.
    Moraglio, A.: Towards a Geometric Unification of Evolutionary Algorithms. Ph.D. thesis, Department of Computer Science, University of Essex, UK, November 2007Google Scholar
  6. 6.
    Moraglio, A., Krawiec, K., Johnson, C.G.: Geometric semantic genetic programming. In: Coello, C.A.C., Cutello, V., Deb, K., Forrest, S., Nicosia, G., Pavone, M. (eds.) PPSN 2012, Part I. LNCS, vol. 7491, pp. 21–31. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  7. 7.
    Vanneschi, L., Castelli, M., Manzoni, L., Silva, S.: A new implementation of geometric semantic GP and its application to problems in pharmacokinetics. In: Krawiec, K., Moraglio, A., Hu, T., Etaner-Uyar, A.Ş., Hu, B. (eds.) EuroGP 2013. LNCS, vol. 7831, pp. 205–216. Springer, Heidelberg (2013) CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Ivo Gonçalves
    • 1
    • 2
  • Sara Silva
    • 1
    • 2
    • 3
  • Carlos M. Fonseca
    • 1
  1. 1.CISUC, Department of Informatics EngineeringUniversity of CoimbraCoimbraPortugal
  2. 2.BioISI - Biosystems & Integrative Sciences Institute, Faculty of SciencesUniversity of LisbonCampo Grande, LisbonPortugal
  3. 3.NOVA IMS, Universidade Nova de LisboaLisbonPortugal

Personalised recommendations