We propose a new type of the digital neuron model by using multi-input multilevel-quanitized digital phase-locked loop (MM-DPLL), where the input is represented by the phase modulated signal. It is shown that this model has the characteristics of the neuron; spatial summation, temporal summation and thresholding. We applied our model to the pattern recognition and to the Hopfield type associative memory, in order to verify that the network by this model can operate properly. In the pattern recognition, we used the perceptron convergence procedure (delta rule), and confirm the possibility of learning by modifying the connection weights. In the associative memory, we confirm that the network can learn five digit patterns of the fundamental memories, and also can recall the correct pattern for the noisy input pattern.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Manabu TOKUNAGA, Iwo SASASE, Shinsaku MORI, "Digital Neuron Model Using Digital Phase-Locked Loop" in IEICE TRANSACTIONS on Information,
vol. E74-D, no. 3, pp. 615-621, March 1991, doi: .
Abstract: We propose a new type of the digital neuron model by using multi-input multilevel-quanitized digital phase-locked loop (MM-DPLL), where the input is represented by the phase modulated signal. It is shown that this model has the characteristics of the neuron; spatial summation, temporal summation and thresholding. We applied our model to the pattern recognition and to the Hopfield type associative memory, in order to verify that the network by this model can operate properly. In the pattern recognition, we used the perceptron convergence procedure (delta rule), and confirm the possibility of learning by modifying the connection weights. In the associative memory, we confirm that the network can learn five digit patterns of the fundamental memories, and also can recall the correct pattern for the noisy input pattern.
URL: https://global.ieice.org/en_transactions/information/10.1587/e74-d_3_615/_p
Copy
@ARTICLE{e74-d_3_615,
author={Manabu TOKUNAGA, Iwo SASASE, Shinsaku MORI, },
journal={IEICE TRANSACTIONS on Information},
title={Digital Neuron Model Using Digital Phase-Locked Loop},
year={1991},
volume={E74-D},
number={3},
pages={615-621},
abstract={We propose a new type of the digital neuron model by using multi-input multilevel-quanitized digital phase-locked loop (MM-DPLL), where the input is represented by the phase modulated signal. It is shown that this model has the characteristics of the neuron; spatial summation, temporal summation and thresholding. We applied our model to the pattern recognition and to the Hopfield type associative memory, in order to verify that the network by this model can operate properly. In the pattern recognition, we used the perceptron convergence procedure (delta rule), and confirm the possibility of learning by modifying the connection weights. In the associative memory, we confirm that the network can learn five digit patterns of the fundamental memories, and also can recall the correct pattern for the noisy input pattern.},
keywords={},
doi={},
ISSN={},
month={March},}
Copy
TY - JOUR
TI - Digital Neuron Model Using Digital Phase-Locked Loop
T2 - IEICE TRANSACTIONS on Information
SP - 615
EP - 621
AU - Manabu TOKUNAGA
AU - Iwo SASASE
AU - Shinsaku MORI
PY - 1991
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E74-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 1991
AB - We propose a new type of the digital neuron model by using multi-input multilevel-quanitized digital phase-locked loop (MM-DPLL), where the input is represented by the phase modulated signal. It is shown that this model has the characteristics of the neuron; spatial summation, temporal summation and thresholding. We applied our model to the pattern recognition and to the Hopfield type associative memory, in order to verify that the network by this model can operate properly. In the pattern recognition, we used the perceptron convergence procedure (delta rule), and confirm the possibility of learning by modifying the connection weights. In the associative memory, we confirm that the network can learn five digit patterns of the fundamental memories, and also can recall the correct pattern for the noisy input pattern.
ER -