|
HKUST Institutional Repository >
Electronic and Computer Engineering >
ECE Master Theses >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1783.1/4375
|
| Title: | Sigma-delta modulation neural networks |
| Authors: | Tang, Patrick Y. H |
| Issue Date: | 1993 |
| Abstract: | Sigma-delta modulation can be used to model the waveforrn coding process of biological neurons. The discrete-time model can greatly simplify the analysis that are nontrivial with traditional continuous time models formulated with differential equations. In the σ-δ modulation neuronal model, we made observations that the neural information is transmitted and received reliably within the neural network due to the noise shaping and 'dithering' inherent in biological neurons.
Aside from the analytical aspect, the model is also a good candidate for VLSI implementations. Sigma-delta neural networks have the same circuit complexity as the pulse coded neural networks. Sigma-delta neural networks is thus an efficient and feasible candidate on large scale implementation of silicon neural systems. |
| Description: | Thesis (M.Phil.)--Hong Kong University of Science and Technology, 1993
vii, 115 leaves : ill. ; 30 cm
HKUST Call Number: Thesis ELEC 1993 Tang |
| URI: | http://hdl.handle.net/1783.1/4375 |
| Appears in Collections: | ECE Master Theses
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| th_redirect.html | | 0Kb | HTML | View/Open |
|
All items in this Repository are protected by copyright, with all rights reserved.
|
