Abstract
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 language | English (US) |
---|---|
Pages (from-to) | 770-773 |
Number of pages | 4 |
Journal | Proceedings - IEEE International Symposium on Circuits and Systems |
Volume | 2 |
State | Published - 1989 |
Externally published | Yes |
Event | IEEE International Symposium on Circuits and Systems 1989, the 22nd ISCAS. Part 1 - Portland, OR, USA Duration: May 8 1989 → May 11 1989 |
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering