Neural Trees and Inheritance

In this project, we have proven that inheritance between neural networks based on tree structures (Neural Trees) is possible and adds accuracy and reduces the time required for classification. We share the knowledge of parents to the child nodes and avoid from duplication in computing. To view our results, see the following articles:

  1.  Shadi Abpeykar, Mehdi Ghatee, An ensemble of RBF neural networks in decision tree structure with knowledge transferring to accelerate multi-classification, Neural Computing and Applications, pp.1-21, 2018. DOI: 10.1007/s00521-018-3543-9
  2. Shadi Abpeykar, Mehdi Ghatee, Hadi Zare, Ensemble decision forest of RBF networks via hybrid feature clustering approach for high-dimensional data classification, Computational Statistics & Data Analysis, 131, (2019) 12-36.
  3. Shadi Abpeykar, Mehdi Ghatee, Neural Trees with Peer-to-Peer and Server-to-Client Knowledge Transferring Models for High-dimensional Data Classification, Expert Systems With Applications, 137 (2019) Pages 281-291, DOI:
    https://doi.org/10.1016/j.eswa.2019.07.003 .
  4. Abpeykar, S. Decision Support System based on Forest of Improved Neural Network Trees on High-dimensional Data, Ph.D. dissertation, Department of Computer Science, Faculty of Mathematics and Computer Science, Amirkabir University of Technology, Tehran, IRAN, December 31, 2018.

Leave a comment

Your email address will not be published. Required fields are marked *