Decision-Based Neural Networks with Signal/Image Classification Applications

S. Y. Kung, J. S. Taur

Research output: Contribution to journalArticlepeer-review

117 Scopus citations


Supervised learning networks based on a decision-based formulation are explored. More specifically, a decision-based neural network (DBNN) is proposed, which combines the perceptron-like learning rule and hierarchical nonlinear network structure. The decision-based mutual training can be applied to both static and temporal pattern recognition problems. For static pattern recognition, two hierarchical structures are proposed: hidden-node and subcluster structures. The relationships between DBNN's and other models (linear perceptron, piecewise-linear perceptron, LVQ, and PNN) are discussed. As to temporal DBNN's, model-based discriminant functions may be chosen to compensate possible temporal variations, such as waveform warping and alignments. Typical examples include DTW distance, prediction error, or likelihood functions. For classification applications, DBNN's are very effective in computation time and performance. This is confirmed by simulations conducted for several applications, including texture classification, OCR, and ECG analysis.

Original languageEnglish (US)
Pages (from-to)170-181
Number of pages12
JournalIEEE Transactions on Neural Networks
Issue number1
StatePublished - Jan 1995
Externally publishedYes

All Science Journal Classification (ASJC) codes

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


Dive into the research topics of 'Decision-Based Neural Networks with Signal/Image Classification Applications'. Together they form a unique fingerprint.

Cite this