Multichannel processing element simulation for neural networks applications
In recent years, hardware implementation of neural networks has received increasing attention from researchers. Various techniques for implementation have been used, such as analog, digital and a hybrid of both. This thesis describes the design and simulation of a digital hardware processing element...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2009
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/19753 |
| _version_ | 1826112552628649984 |
|---|---|
| author | Cao, En |
| author2 | Chan, Choong Wah |
| author_facet | Chan, Choong Wah Cao, En |
| author_sort | Cao, En |
| collection | NTU |
| description | In recent years, hardware implementation of neural networks has received increasing attention from researchers. Various techniques for implementation have been used, such as analog, digital and a hybrid of both. This thesis describes the design and simulation of a digital hardware processing element. It focuses on the implementation of digital neural hardware based on bit-serial transmission and information processing which is known as the Pulse-Stream Implementation (PSI). Stochastic computing is an important PSI technique, and currently two techniques of stochastic computing are in use; they are binary stochastic computing (BSC) and pulse density modulation (PDM). As a model of neural hardware, the mapping network for modelling of freeform surfaces is discussed in geometrical terms. |
| first_indexed | 2024-10-01T03:08:55Z |
| format | Thesis |
| id | ntu-10356/19753 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:08:55Z |
| publishDate | 2009 |
| record_format | dspace |
| spelling | ntu-10356/197532023-07-04T15:31:48Z Multichannel processing element simulation for neural networks applications Cao, En Chan, Choong Wah School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering In recent years, hardware implementation of neural networks has received increasing attention from researchers. Various techniques for implementation have been used, such as analog, digital and a hybrid of both. This thesis describes the design and simulation of a digital hardware processing element. It focuses on the implementation of digital neural hardware based on bit-serial transmission and information processing which is known as the Pulse-Stream Implementation (PSI). Stochastic computing is an important PSI technique, and currently two techniques of stochastic computing are in use; they are binary stochastic computing (BSC) and pulse density modulation (PDM). As a model of neural hardware, the mapping network for modelling of freeform surfaces is discussed in geometrical terms. Master of Engineering 2009-12-14T06:33:59Z 2009-12-14T06:33:59Z 1994 1994 Thesis http://hdl.handle.net/10356/19753 en Nanyang Technological University 144 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Electrical and electronic engineering Cao, En Multichannel processing element simulation for neural networks applications |
| title | Multichannel processing element simulation for neural networks applications |
| title_full | Multichannel processing element simulation for neural networks applications |
| title_fullStr | Multichannel processing element simulation for neural networks applications |
| title_full_unstemmed | Multichannel processing element simulation for neural networks applications |
| title_short | Multichannel processing element simulation for neural networks applications |
| title_sort | multichannel processing element simulation for neural networks applications |
| topic | DRNTU::Engineering::Electrical and electronic engineering |
| url | http://hdl.handle.net/10356/19753 |
| work_keys_str_mv | AT caoen multichannelprocessingelementsimulationforneuralnetworksapplications |