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 solve or at least get a good approximation the solution, and neural networks are known assimilate that complexity by deepening widening their topology in order increase level non-linearity needed for better approximation. However, compact topologies always preferred deeper ones as they offer advantage using less computational units parameters. This compacity comes price reduced thus, limited solution search space. We propose 1-Dimensional Polynomial Neural Network (1DPNN) model uses automatic polynomial kernel estimation Convolutional Networks (1DCNNs) introduces high degree from first layer which can compensate need deep and/or wide topologies. show this enables yield results with spatial than regular 1DCNN on various classification regression related audio signals, even though it more neuronal level. The experiments were conducted three publicly available datasets demonstrate that, tackled, proposed extract relevant information data time memory.