Backpropagation with N -D Vector-Valued Neurons Using Arbitrary Bilinear Products
Journal
IEEE Transactions on Neural Networks and Learning Systems
Journal Volume
31
Journal Issue
7
Pages
2638 - 2652
Date Issued
2020
Author(s)
Abstract
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.
Subjects
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
Type
journal article