TY - GEN
T1 - Implementation of quadric perceptron with hardlims activation function in a FPGA for nonlinear pattern classification
AU - Garcia, Raymundo Cordero
AU - Suemitsu, Walter Issamu
AU - Pinto, Joao Onofre Pereira
AU - Soares, Andre Muniz
PY - 2013
Y1 - 2013
N2 - This paper deals with the design and implementation of an artificial neural network for pattern classification in the FPGA EP2C20F484C7. A perceptron with quadratic decision boundary is used as nonlinear classification system, but using a hardlims as activation function, instead of a sigmoid function. The training algorithm is similar to the used in conventional perceptron. The elimination of the sigmoid function makes simpler the implementation of quadratic perceptrons. As the mentioned FPGA does not do neither float-point nor fixed-point multiplications, the synaptic weights were normalized to integers. The proposed quadratic perceptron is tested in a set of classification problems and compared with multilayer perceptron. Example of experimental implementation of the proposed classification system is shown, including parameters about computational cost.
AB - This paper deals with the design and implementation of an artificial neural network for pattern classification in the FPGA EP2C20F484C7. A perceptron with quadratic decision boundary is used as nonlinear classification system, but using a hardlims as activation function, instead of a sigmoid function. The training algorithm is similar to the used in conventional perceptron. The elimination of the sigmoid function makes simpler the implementation of quadratic perceptrons. As the mentioned FPGA does not do neither float-point nor fixed-point multiplications, the synaptic weights were normalized to integers. The proposed quadratic perceptron is tested in a set of classification problems and compared with multilayer perceptron. Example of experimental implementation of the proposed classification system is shown, including parameters about computational cost.
KW - Artificial neural networks
KW - FPGA
KW - decision boundary
KW - multilayer perceptron
KW - quadratic perceptron
UR - http://www.scopus.com/inward/record.url?scp=84893590266&partnerID=8YFLogxK
U2 - 10.1109/IECON.2013.6699512
DO - 10.1109/IECON.2013.6699512
M3 - Conference contribution
AN - SCOPUS:84893590266
SN - 9781479902248
T3 - IECON Proceedings (Industrial Electronics Conference)
SP - 2432
EP - 2437
BT - Proceedings, IECON 2013 - 39th Annual Conference of the IEEE Industrial Electronics Society
T2 - 39th Annual Conference of the IEEE Industrial Electronics Society, IECON 2013
Y2 - 10 November 2013 through 14 November 2013
ER -