Abstract
In this chapter, we present a series of experiments in order to demonstrate the capabilities of geometric neural networks. We show cases of learning of a high nonlinear mapping and prediction. In the second part experiments of multiclass classification, object recognition, and robot trajectories interpolation using CSVM are included.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The network output is expressed as \(X = xe_1e_2 + ye_2e_3+ze_3e_1\).
- 2.
The dimension of this geometric algebra is \(2^2=4\).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2019 Springer International Publishing AG, part of Springer Nature
About this chapter
Cite this chapter
Bayro-Corrochano, E. (2019). Applications in Neurocomputing. In: Geometric Algebra Applications Vol. I. Springer, Cham. https://doi.org/10.1007/978-3-319-74830-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-74830-6_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-74828-3
Online ISBN: 978-3-319-74830-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)