Time Series Compression using Quaternion Valued Neural Networks and Quaternion Backpropagation

arXiv:2403.11722v1 Announce Type: new
Abstract: We propose a novel quaternionic time-series compression methodology where we divide a long time-series into segments of data, extract the min, max, mean and standard deviation of these chunks as representative features and encapsulate them in a quaternion, yielding a quaternion valued time-series. This time-series is processed using quaternion valued neural network layers, where we aim to preserve the relation between these features through the usage of the Hamilton product. To train this quaternion neural …

abstract arxiv backpropagation compression cs.lg data deviation extract features max mean methodology networks neural networks novel series standard them time series type