https://scholars.lib.ntu.edu.tw/handle/123456789/581374
標題: | Backpropagation with N -D Vector-Valued Neurons Using Arbitrary Bilinear Products | 作者: | Fan Z.-C Chan T.-S.T YI-HSUAN YANG JYH-SHING JANG |
關鍵字: | Backpropagation; Convolution; Deep learning; Image denoising; Neural networks; Circular convolutions; Multispectral images; Neural architectures; Neural learning; Neural networks (NNS); Proof of concept; Singing voice separations; Training data; Vectors; article; back propagation; nerve cell; proof of concept; singing; voice | 公開日期: | 2020 | 卷: | 31 | 期: | 7 | 起(迄)頁: | 2638 - 2652 | 來源出版物: | IEEE Transactions on Neural Networks and Learning Systems | 摘要: | Vector-valued neural learning has emerged as a promising direction in deep learning recently. Traditionally, training data for neural networks (NNs) are formulated as a vector of scalars; however, its performance may not be optimal since associations among adjacent scalars are not modeled. In this article, we propose a new vector neural architecture called the Arbitrary BIlinear Product NN (ABIPNN), which processes information as vectors in each neuron, and the feedforward projections are defined using arbitrary bilinear products. Such bilinear products can include circular convolution, 7-D vector product, skew circular convolution, reversed-time circular convolution, or other new products that are not seen in the previous work. As a proof-of-concept, we apply our proposed network to multispectral image denoising and singing voice separation. Experimental results show that ABIPNN obtains substantial improvements when compared to conventional NNs, suggesting that associations are learned during training. ? 2012 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85088146785&doi=10.1109%2fTNNLS.2019.2933882&partnerID=40&md5=cba7064d5f81cfb6d13a1735f63f7b6b https://scholars.lib.ntu.edu.tw/handle/123456789/581374 |
ISSN: | 2162237X | DOI: | 10.1109/TNNLS.2019.2933882 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。