Abstract
In current practice, tapped delay line models such as the time delay neural network (TDNN) are commonly implemented using a direct form structure. In this paper, we show that the problem of high parameter sensitivity, well known in linear systems, also applies to nonlinear models such as the TDNN. To overcome the consequent numerical problems, we propose a cascade form TDNN (CTDNN) and show its advantages over the commonly used direct form TDNN.
Original language | English (US) |
---|---|
Title of host publication | Neural Networks for Signal Processing - Proceedings of the IEEE Workshop |
Publisher | IEEE |
Pages | 44-53 |
Number of pages | 10 |
State | Published - 1997 |
Event | Proceedings of the 1997 7th IEEE Workshop on Neural Networks for Signal Processing, NNSP'97 - Amelia Island, FL, USA Duration: Sep 24 1997 → Sep 26 1997 |
Other
Other | Proceedings of the 1997 7th IEEE Workshop on Neural Networks for Signal Processing, NNSP'97 |
---|---|
City | Amelia Island, FL, USA |
Period | 9/24/97 → 9/26/97 |
All Science Journal Classification (ASJC) codes
- Signal Processing
- Software
- Electrical and Electronic Engineering