The 2006 IEEE International Joint Conference on Neural Network Proceedings · 2006 · 38 citations · 7 references
ComputingComputer ScienceArtificial IntelligenceMachine LearningMemoryNeural ModelingNeural NetworksNeural RepresentationPattern RecognitionAttractor NetworksAttractorsHebbian Learning RulesHopfield NetworksNeural Network ModelingQuaternion RepresentationRecurrent Neural NetworksTopology Of Neural Networks
Associative memory by Hopfleld-type recurrent neural networks with quaternionic algebra, called quaternionic Hopfield neural network, is proposed in this paper. The variables in the network are represented by quaternions of four dimensional hypercomplex numbers. The neuron model, the energy function, and the Hebbian rule for embedding patterns into the network are introduced. The properties of this network are analyzed concretely through examples of the network with 3 and 4 quaternion neurons. It is demonstrated that there exist fixed attractors in the network, i.e., the pattern association from test pattern close to a stored pattern is possible in the quaternionic network, as in real-valued Hopfleld networks.
7
Quaternion neural network with geometrical operators
Nobuyuki Matsui, Teijiro Isokawa, Hiromi Kusamichi et al. · Journal of Intelligent & Fuzzy Systems · 2004 · 215 citations
Multilayer Perceptrons to Approximate Quaternion Valued Functions
P. Arena, Luigi Fortuna, Giovanni Muscato et al. · Neural Networks · 1997 · 156 citations