DocumentCode :
857318
Title :
Modulated Hebb-Oja learning Rule-a method for principal subspace analysis
Author :
Jankovic, Marko V. ; Ogawa, Hidemitsu
Author_Institution :
Electr. Eng. Inst. "Nikola Tesla", Belgrade, Serbia
Volume :
17
Issue :
2
fYear :
2006
fDate :
3/1/2006 12:00:00 AM
Firstpage :
345
Lastpage :
356
Abstract :
This paper presents analysis of the recently proposed modulated Hebb-Oja (MHO) method that performs linear mapping to a lower-dimensional subspace. Principal component subspace is the method that will be analyzed. Comparing to some other well-known methods for yielding principal component subspace (e.g., Oja\´s Subspace Learning Algorithm), the proposed method has one feature that could be seen as desirable from the biological point of view-synaptic efficacy learning rule does not need the explicit information about the value of the other efficacies to make individual efficacy modification. Also, the simplicity of the "neural circuits" that perform global computations and a fact that their number does not depend on the number of input and output neurons, could be seen as good features of the proposed method.
Keywords :
learning (artificial intelligence); neural nets; principal component analysis; linear mapping; lower-dimensional subspace; modulated Hebb-Oja learning rule; neural circuits; principal component subspace analysis; synaptic efficacy learning rule; Algorithm design and analysis; Biology computing; Circuits; Data compression; Feature extraction; Neural networks; Neurons; Performance analysis; Principal component analysis; Vectors; Learning algorithm; neural networks; principal component analysis (PCA); principal subspace analysis (PSA); Algorithms; Artificial Intelligence; Computer Simulation; Decision Support Techniques; Models, Theoretical; Neural Networks (Computer); Numerical Analysis, Computer-Assisted; Pattern Recognition, Automated;
fLanguage :
English
Journal_Title :
Neural Networks, IEEE Transactions on
Publisher :
ieee
ISSN :
1045-9227
Type :
jour
DOI :
10.1109/TNN.2005.863455
Filename :
1603621
Link To Document :
بازگشت