Unifying viewpoint of multilayer perceptrons and hidden Markov models

J. N. Hwang, S. Y. Kung

Research output: Contribution to journalConference articlepeer-review

4 Scopus citations


A generic iterative model for artificial neural networks (ANNs) is proposed which covers a wide variety of existing neural networks: single-layer feedback networks, multilayer feedforward networks, hierarchical competitive networks, and hidden Markov models. From the phase-retrieve point of view, the hidden Markov models described by the trellis structure can be regarded as a homogeneous (recurrent) multilayer perceptron with nonlinear squashing activation function. From the learning-phase point of view, it is shown that the additive gradient descent (ascent) approaches can be used to derive the back-propagation learning in the multilayer perceptrons. On the other hand, the multiplicative gradient descent (ascent) approach can be successfully applied to the trellis structure and used to derive the Baum-Welch reestimation formulation in the hidden Markov models.

Original languageEnglish (US)
Pages (from-to)770-773
Number of pages4
JournalProceedings - IEEE International Symposium on Circuits and Systems
StatePublished - 1989
Externally publishedYes
EventIEEE International Symposium on Circuits and Systems 1989, the 22nd ISCAS. Part 1 - Portland, OR, USA
Duration: May 8 1989May 11 1989

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering


Dive into the research topics of 'Unifying viewpoint of multilayer perceptrons and hidden Markov models'. Together they form a unique fingerprint.

Cite this