The goal of this paper is to test three classes of neural network (NN) architectures based on four-dimensional (4D) hypercomplex algebras for multivariate time series forecasting. We evaluate ...
Quaternion-valued neural networks employ quaternions – four-dimensional hypercomplex numbers – as fundamental representational units, allowing weights, inputs and activations to be encoded compactly ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results