Multilayer feedforward networks are universal approximators
Neural Networks
Parallel distributed processing: explorations in the microstructure, vol. 2: psychological and biological models
Invariant body kinematics. II: reaching and neurogeometry
Neural Networks
Playing billiards in version space
Neural Computation
Generalized homogeneous coordinates for computational geometry
Geometric computing with Clifford algebras
Recognizing Planar Objects Using Invariant Image Features
Recognizing Planar Objects Using Invariant Image Features
Computer Vision: Three-Dimensional Data from Images
Computer Vision: Three-Dimensional Data from Images
Improving Recurrent CSVM Performance for Robot Navigation on Discrete Labyrinths
CIARP '09 Proceedings of the 14th Iberoamerican Conference on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
An Iterative Method for Deciding SVM and Single Layer Neural Network Structures
Neural Processing Letters
A conic higher order neuron based on geometric algebra and its implementation
MICAI'12 Proceedings of the 11th Mexican international conference on Advances in Computational Intelligence - Volume Part II
Hi-index | 0.01 |
This paper shows the design and use of feed-forward neural networks and the support vector machines (SVM) in the coordinate-free mathematical system of the Clifford geometric algebra. We compare the McCulloch-Pitts neuron and the geometric neuron. An interesting case of the geometric neuron is the conformal neuron which can be used for RBF networks and SVM. The paper presents the generalization of the real- and complex-valued multilayer perceptron (MLP) to the Clifford valued multilayer perceptron. The paper studies also the multivector support vector machines (MSVM) which are SVMs for processing multivectors. For that we design kernels involving Clifford products. The resultant kernel resembles a sort of polynomial kernel using a multivector representation. In the context of SVMs an important contribution of the paper is the generalization of the real- and complex-valued SVM classifiers over the hyper-complex numbers. This Clifford valued SVM accepts multiple multivector inputs and it is a multi-class classifier. For the preprocessing the authors introduce a promising geometric method utilizing Clifford moments. This method is applied together with geometric MLPs for tasks of 2D pattern recognition. The experimental part shows applications of SVM using the conformal neuron and Clifford kernels. We include challenging applications of the Clifford SVM classifier for nonlinear separable problems. The authors believe that the use of the MLPs and SVMs in the geometric algebra framework expands their sphere of applicability for multivector learning in graded spaces.