Constructive neural-network learning algorithms for pattern classification

Rajesh Parekh, Jihoon Yang, Vasant Honavar

Research output: Contribution to journalArticlepeer-review

194 Scopus citations


Constructive learning algorithms offer an attractive approach for the incremental construction of near-minimal neural-network architectures for pattern classification. They help overcome the need for ad hoc and often inappropriate choices of network topology in algorithms that search for suitable weights in a priori fixed network architectures. Several such algorithms are proposed in the literature and shown to converge to zero classification errors (under certain assumptions) on tasks that involve learning a binary to binary mapping (i.e., classification problems involving binary-valued input attributes and two output categories). We present two constructive learning algorithms MPyramid-real and MTiling-real that extend the pyramid and tiling algorithms, respectively, for learning real to M-ary mappings (i.e., classification problems involving real-valued input attributes and multiple output classes). We prove the convergence of these algorithms and empirically demonstrate their applicability to practical pattern classification problems. Additionally, we show how the incorporation of a local pruning step can eliminate several redundant neurons from MTiling-real networks.

Original languageEnglish (US)
Pages (from-to)436-451
Number of pages16
JournalIEEE Transactions on Neural Networks
Issue number2
StatePublished - 2000

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence


Dive into the research topics of 'Constructive neural-network learning algorithms for pattern classification'. Together they form a unique fingerprint.

Cite this