TY - GEN
T1 - Application of Directional Vectors for Independent Subspaces in the Bio-Inspired Networks
AU - Ishii, Naohiro
AU - Iwata, Kazunori
AU - Odagiri, Kazuya
AU - Matsuo, Tokuro
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
PY - 2024
Y1 - 2024
N2 - Machine learning, deep learning and neural networks are extensively developed in many fields, in which neural network architectures have shown a variety of applications. However, there is a need for explainable fundamentals in complex neural networks. It is important to know how the sensory information in neural networks develops to the higher-level processing for classification and learning. In this paper, it is shown that bio-inspired networks are useful for the explanation of network functions. First, the asymmetric network is created based on the biological retinal network with nonlinear functions. Second, the classification performance of the asymmetric network is compared to the conventional symmetric network. Prominent characteristic in the biological networks is sensitive to the motion intensity changes in their visual environments. Here, it is shown that the adjacent neurons create sensory directional information in the movements. Further, directional vectors are generated on the activities of the adjacent neurons caused by the intensity changes of the input. These vectors are useful for the generation of independent subspaces, which connect from the sensory information to the higher-level functions in networks.
AB - Machine learning, deep learning and neural networks are extensively developed in many fields, in which neural network architectures have shown a variety of applications. However, there is a need for explainable fundamentals in complex neural networks. It is important to know how the sensory information in neural networks develops to the higher-level processing for classification and learning. In this paper, it is shown that bio-inspired networks are useful for the explanation of network functions. First, the asymmetric network is created based on the biological retinal network with nonlinear functions. Second, the classification performance of the asymmetric network is compared to the conventional symmetric network. Prominent characteristic in the biological networks is sensitive to the motion intensity changes in their visual environments. Here, it is shown that the adjacent neurons create sensory directional information in the movements. Further, directional vectors are generated on the activities of the adjacent neurons caused by the intensity changes of the input. These vectors are useful for the generation of independent subspaces, which connect from the sensory information to the higher-level functions in networks.
KW - asymmetric and symmetric networks
KW - classification performance of networks
KW - generation of the directional vectors
KW - independent subspaces
UR - https://www.scopus.com/pages/publications/85198941186
UR - https://www.scopus.com/pages/publications/85198941186#tab=citedBy
U2 - 10.1007/978-3-031-62495-7_34
DO - 10.1007/978-3-031-62495-7_34
M3 - Conference contribution
AN - SCOPUS:85198941186
SN - 9783031624940
T3 - Communications in Computer and Information Science
SP - 450
EP - 462
BT - Engineering Applications of Neural Networks - 25th International Conference, EANN 2024, Proceedings
A2 - Iliadis, Lazaros
A2 - Papaleonidas, Antonios
A2 - Maglogiannis, Ilias
A2 - Pimenidis, Elias
A2 - Jayne, Chrisina
PB - Springer Science and Business Media Deutschland GmbH
T2 - 25th International Conference on Engineering Applications of Neural Networks, EANN 2024
Y2 - 27 June 2024 through 30 June 2024
ER -