TY - JOUR
T1 - Analog circuit design and implementation of an adaptive resonance theory (ART) neural network architecture
AU - Ho, Ching S.
AU - Liou, Juin J.
AU - Georgiopoulos, Michael
AU - Heileman, Gregory L.
AU - Christodoulou, Christos
N1 - Funding Information:
This work was supported in part by the Florida High Technology Council, and in part by the Division of Sponsored Research at UCF.
Funding Information:
Acknowledgement: This work was supported in part by the Florida High Technology Council, and in part by the
Publisher Copyright:
© 1993 SPIE. All rights reserved.
PY - 1993/9/2
Y1 - 1993/9/2
N2 - This paper presents an analog circuit implementation for an adaptive resonance theory neural network architecture, called the augmented ART-1 neural network (AART1-NN). The AART1-NN is a modification of the popular ART1-NN, developed by Carpenter and Grossberg, and it exhibits the same behavior as the ART1-NN. The AART1-NN is a real-time model, and has the ability to classify an arbitrary set of binary input patterns into different clusters. The design of the AART1-NN circuit is based on a set of coupled nonlinear differential equations that constitute the AART1-NN model. The circuit is implemented by utilizing analog electronic components, such as, operational amplifiers, transistors, capacitors, and resistors. The implemented circuit is verified using the PSpice circuit simulator, running on Sun workstations. Results obtained from the PSpice circuit simulation compare favorably with simulation results produced by solving the differential equations numerically. The prototype system developed here can be used as a building block for larger AART1-NN architectures, as well as for other types of ART architectures that involve the AART1-NN model.
AB - This paper presents an analog circuit implementation for an adaptive resonance theory neural network architecture, called the augmented ART-1 neural network (AART1-NN). The AART1-NN is a modification of the popular ART1-NN, developed by Carpenter and Grossberg, and it exhibits the same behavior as the ART1-NN. The AART1-NN is a real-time model, and has the ability to classify an arbitrary set of binary input patterns into different clusters. The design of the AART1-NN circuit is based on a set of coupled nonlinear differential equations that constitute the AART1-NN model. The circuit is implemented by utilizing analog electronic components, such as, operational amplifiers, transistors, capacitors, and resistors. The implemented circuit is verified using the PSpice circuit simulator, running on Sun workstations. Results obtained from the PSpice circuit simulation compare favorably with simulation results produced by solving the differential equations numerically. The prototype system developed here can be used as a building block for larger AART1-NN architectures, as well as for other types of ART architectures that involve the AART1-NN model.
UR - http://www.scopus.com/inward/record.url?scp=85075827962&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85075827962&partnerID=8YFLogxK
U2 - 10.1117/12.152540
DO - 10.1117/12.152540
M3 - Conference article
AN - SCOPUS:85075827962
VL - 1965
SP - 244
EP - 255
JO - Proceedings of SPIE - The International Society for Optical Engineering
JF - Proceedings of SPIE - The International Society for Optical Engineering
SN - 0277-786X
T2 - Applications of Artificial Neural Networks IV 1993
Y2 - 11 April 1993 through 16 April 1993
ER -