Initialization of neural networks by means of decision trees

Irena Ivanova, Miroslav Kubat

Research output: Contribution to journalArticlepeer-review

34 Scopus citations


The performance of neural networks is known to be sensitive to the initial weight setting and architecture (the number of hidden layers and neurons in these layers). This shortcoming can be alleviated if some approximation of the target concept in terms of a logical description is available. The paper reports a successful attempt to initialize neural networks using decision-tree generators. The TBNN (tree-based neural net) system compares very favourably with other learners in terms of classification accuracy for unseen data, and it is also computationally less demanding than the back propagation algorithm applied to a randomly initialized multilayer perceptron. The behavior of the system is first studied for specially designed artificial data. Then, its performance is demonstrated by a real-world application.

Original languageEnglish (US)
Pages (from-to)333-344
Number of pages12
JournalKnowledge-Based Systems
Issue number6
StatePublished - Dec 1995
Externally publishedYes


  • decision-tree generators
  • neural networks

ASJC Scopus subject areas

  • Management Information Systems
  • Artificial Intelligence
  • Software
  • Information Systems and Management


Dive into the research topics of 'Initialization of neural networks by means of decision trees'. Together they form a unique fingerprint.

Cite this