TY - GEN
T1 - GoogLeDNet
T2 - 15th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2023
AU - Song, Yaotong
AU - He, Houtian
AU - Zhang, Zhiming
AU - Li, Jiayi
AU - Liu, Zhipeng
AU - Gao, Shangce
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - The neuron model is a widely-used approach for classification problems that imitates the behavior of neurons in the brain. However, most existing neuron models do not account for the non-linear characteristics of dendrites and synapses. To address this limitation, we propose a novel deep learning model, called GoogLeDNet, which combines the GoogLeNet architecture with the dendritic neuron model (DNM). By incorporating the non-linear characteristics of dendrites and synapses, our model closely resembles the structure of biological neurons and demonstrates superior performance on the CelebA gender classification dataset. Compared to other baseline models, including AlexNet, MobileNet, ShuffleNet, and GoogLeNet, our model achieves an accuracy of 93.3% and an F1 score of 93.2%.
AB - The neuron model is a widely-used approach for classification problems that imitates the behavior of neurons in the brain. However, most existing neuron models do not account for the non-linear characteristics of dendrites and synapses. To address this limitation, we propose a novel deep learning model, called GoogLeDNet, which combines the GoogLeNet architecture with the dendritic neuron model (DNM). By incorporating the non-linear characteristics of dendrites and synapses, our model closely resembles the structure of biological neurons and demonstrates superior performance on the CelebA gender classification dataset. Compared to other baseline models, including AlexNet, MobileNet, ShuffleNet, and GoogLeNet, our model achieves an accuracy of 93.3% and an F1 score of 93.2%.
KW - Classification
KW - Deep Learning
KW - Dendritic neuron model
UR - http://www.scopus.com/inward/record.url?scp=85174675180&partnerID=8YFLogxK
U2 - 10.1109/IHMSC58761.2023.00018
DO - 10.1109/IHMSC58761.2023.00018
M3 - 会議への寄与
AN - SCOPUS:85174675180
T3 - Proceedings - 2023 15th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2023
SP - 41
EP - 44
BT - Proceedings - 2023 15th International Conference on Intelligent Human-Machine Systems and Cybernetics, IHMSC 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 26 August 2023 through 27 August 2023
ER -