1-Dimensional Polynomial Neural Networks for audio signal related problems

In addition to being extremely non-linear, modern problems require millions if not billions of parameters to solve or at least to get a good approximation of the solution, and neural networks are known to assimilate that complexity by deepening and widening their topology in order to increase the le...

Full description

Saved in:
Bibliographic Details
Published in:Knowledge-based systems 2022-03, Vol.240, p.108174, Article 108174
Main Authors: Ben Abdallah, Habib, Henry, Christopher J., Ramanna, Sheela
Format: Article
Language:English
Subjects:
Approximation
Artificial neural networks
Audio signal processing
Audio signals
Complexity
Convolutional neural networks
Denoising
Machine learning
Mathematical models
Network topologies
Neural networks
Nonlinearity
Parameters
Polynomial approximation
Polynomials
Speech processing
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In addition to being extremely non-linear, modern problems require millions if not billions of parameters to solve or at least to get a good approximation of the solution, and neural networks are known to assimilate that complexity by deepening and widening their topology in order to increase the level of non-linearity needed for a better approximation. However, compact topologies are always preferred to deeper ones as they offer the advantage of using less computational units and less parameters. This compacity comes at the price of reduced non-linearity and thus, of limited solution search space. We propose the 1-Dimensional Polynomial Neural Network (1DPNN) model that uses automatic polynomial kernel estimation for 1-Dimensional Convolutional Neural Networks (1DCNNs) and that introduces a high degree of non-linearity from the first layer which can compensate the need for deep and/or wide topologies. We show that this non-linearity enables the model to yield better results with less computational and spatial complexity than a regular 1DCNN on various classification and regression problems related to audio signals, even though it introduces more computational and spatial complexity on a neuronal level. The experiments were conducted on three publicly available datasets and demonstrate that, on the problems that were tackled, the proposed model can extract more relevant information from the data than a 1DCNN in less time and with less memory.
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2022.108174