Constructing Convolutional Neural Networks Based on Quaternion
説明
A convolutional neural network based on quaternion, a four-dimensional hypercomplex number system, is proposed and evaluated in this paper. Called Quaternionic Convolutional Neural Networks (QCNNs), these networks can accept and operate three-dimensional signals by neurons in the networks. The performances of the proposed networks are investigated through classification of CIFAR-10 color images, and it is shown that the proposed QCNN outperforms a conventional (real-valued) CNN.
収録刊行物
-
- 2020 International Joint Conference on Neural Networks (IJCNN)
-
2020 International Joint Conference on Neural Networks (IJCNN) 1-6, 2020-07-01
IEEE