Abstract
Neural networks with values in multidimensional domains have been intensively studied over the last few years. This paper introduces octonion-valued neural networks, for which the inputs, outputs, weights and biases are all octonions. They represent a generalization of the complex- and quaternion-valued neural networks, that do not fall into the category of Clifford-valued neural networks, because, unlike Clifford algebras, the octonion algebra is not associative. The full deduction of the gradient descent algorithm for training octonion-valued feedforward neural networks is presented. Testing of the proposed network is done using two synthetic function approximation problems and a time series prediction application.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
