DocumentCode
2951749
Title
Design of bit-stream neuron based on direct Σ-Δ signal process
Author
Liang, Yong ; Meng, Qiao ; Wang, Zhigong ; Guo, XiaoDan
Author_Institution
Inst. of RF- & OE-ICs, Southeast Univ., Nanjing, China
fYear
2009
fDate
13-15 Nov. 2009
Firstpage
1
Lastpage
3
Abstract
A novel method to build an artificial neuron is presented. All the modules in the artificial neuron are bit-stream units based on direct Σ-Δ signal process. The fundamental modules used in bit-stream artificial neuron, i.e., adder, multiplier, activation function unit, were implemented in integrated circuit (IC) form or Field Programmable Gate Array (FPGA). The principle, the structure and the performance of the modules are discussed.
Keywords
field programmable gate arrays; integrated circuits; neural nets; sigma-delta modulation; signal processing; FPGA; IC; artificial neuron; bit-stream neuron design; field programmable gate array; integrated circuit; sigma-delta processing; signal process; Sigma Delta; bit-stream; component; neuron; signal process;
fLanguage
English
Publisher
ieee
Conference_Titel
Wireless Communications & Signal Processing, 2009. WCSP 2009. International Conference on
Conference_Location
Nanjing
Print_ISBN
978-1-4244-4856-2
Electronic_ISBN
978-1-4244-5668-0
Type
conf
DOI
10.1109/WCSP.2009.5371617
Filename
5371617
Link To Document