Abstract
This work explores Volterra kernel extraction using feed forward neural network (FFN) with monomial power series (MPS) activation function for high speed I/O buffer behavioral modeling. The proposed method demonstrates a higher level of accuracy and flexible order truncation. The proposed method is validated using a computer simulated Weiner system with second order nonlinearity. A case study with a real high speed I/O buffer is also conducted and discussed.
Original language | English (US) |
---|---|
Title of host publication | 2019 Joint International Symposium on Electromagnetic Compatibility, Sapporo and Asia-Pacific International Symposium on Electromagnetic Compatibility, EMC Sapporo/APEMC 2019 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 564-567 |
Number of pages | 4 |
ISBN (Electronic) | 9784885523229 |
DOIs | |
State | Published - Jun 2019 |
Event | 2019 Joint International Symposium on Electromagnetic Compatibility, Sapporo and Asia-Pacific International Symposium on Electromagnetic Compatibility, EMC Sapporo/APEMC 2019 - Sapporo, Japan Duration: Jun 3 2019 → Jun 7 2019 |
Publication series
Name | 2019 Joint International Symposium on Electromagnetic Compatibility, Sapporo and Asia-Pacific International Symposium on Electromagnetic Compatibility, EMC Sapporo/APEMC 2019 |
---|
Conference
Conference | 2019 Joint International Symposium on Electromagnetic Compatibility, Sapporo and Asia-Pacific International Symposium on Electromagnetic Compatibility, EMC Sapporo/APEMC 2019 |
---|---|
Country/Territory | Japan |
City | Sapporo |
Period | 6/3/19 → 6/7/19 |
Keywords
- Behavior Modeling
- Feed Forward Neural Network
- Signal Integrity
- Volterra Series
ASJC Scopus subject areas
- Computer Networks and Communications
- Hardware and Architecture
- Information Systems and Management