Title :
Self-organizing maps with a single neuron
Author :
Georgiou, George M. ; Voigt, K.
Author_Institution :
Sch. of Comput. Sci. & Eng., California State Univ., San Bernardino, CA, USA
Abstract :
Self-organization is explored with a single complex-valued quadratic neuron. The output is the complex plane. A virtual grid is used to provide desired outputs for each input. Experiments have shown that training is fast. A quadratic neuron with the new training algorithm has been shown to have clustering properties. Data that are in a cluster in the input space tend to cluster on the complex plane. The speed of training and operation allows for efficient high-dimensional data exploration and for real-time critical applications.
Keywords :
learning (artificial intelligence); pattern clustering; real-time systems; self-organising feature maps; clustering property; high-dimensional data exploration; real-time critical applications; self-organizing maps; single complex-valued quadratic neuron; training algorithm; virtual grid; Clustering algorithms; Iris; Mean square error methods; Neurons; Self-organizing feature maps; Training; Vectors;
Conference_Titel :
Neural Networks (IJCNN), The 2013 International Joint Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4673-6128-6
DOI :
10.1109/IJCNN.2013.6706843
