TY - JOUR
T1 - A solution for the N-bit parity problem using a single translated multiplicative neuron
AU - Iyoda, Eduardo Masato
AU - Nobuhara, Hajime
AU - Hirota, Kaoru
PY - 2003/12
Y1 - 2003/12
N2 - A solution to the N-bit parity problem employing a single multiplicative neuron model, called translated multiplicative neuron (πt-neuron), is proposed. The πt-neuron presents the following advantages: (a) ∀N ≥ 1, only 1 πt-neuron is necessary, with a threshold activation function and parameters defined within a specific interval; (b) no learning procedures are required; and (c) the computational cost is the same as the one associated with a simple McCulloch-Pitts neuron. Therefore, the πt-neuron solution to the N-bit parity problem has the lowest computational cost among the neural solutions presented to date.
AB - A solution to the N-bit parity problem employing a single multiplicative neuron model, called translated multiplicative neuron (πt-neuron), is proposed. The πt-neuron presents the following advantages: (a) ∀N ≥ 1, only 1 πt-neuron is necessary, with a threshold activation function and parameters defined within a specific interval; (b) no learning procedures are required; and (c) the computational cost is the same as the one associated with a simple McCulloch-Pitts neuron. Therefore, the πt-neuron solution to the N-bit parity problem has the lowest computational cost among the neural solutions presented to date.
KW - Multiplicative neurons
KW - N-bit parity problem
KW - Neural networks
UR - http://www.scopus.com/inward/record.url?scp=0842343634&partnerID=8YFLogxK
U2 - 10.1023/b:nepl.0000011147.74207.8c
DO - 10.1023/b:nepl.0000011147.74207.8c
M3 - Article
AN - SCOPUS:0842343634
SN - 1370-4621
VL - 18
SP - 213
EP - 218
JO - Neural Processing Letters
JF - Neural Processing Letters
IS - 3
ER -