A new probabilistic approach to on-line learning in artificial neural networks

Authors:
Marko V. Jankovic;Neil Rubens
Affiliations:
Institute of Electrical Engineering "Nikola Tesla", Belgrade, Serbia;Graduate School of Information Systems, University of Electro-Communications, Tokyo, Japan
Venue:
ASMCSS'09 Proceedings of the 3rd International Conference on Applied Mathematics, Simulation, Modelling, Circuits, Systems and Signals
Year:
2009

Citing 10
Cited 1

Mixtures of probabilistic principal component analyzers

Neural Computation
Quantum computation and quantum information

Quantum computation and quantum information
Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications

Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications
Robust probabilistic projections

ICML '06 Proceedings of the 23rd international conference on Machine learning
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Learning principal directions: Integrated-squared-error minimization

Neurocomputing
Robust probabilistic PCA with missing data and contribution analysis for outlier detection

Computational Statistics & Data Analysis
Bayesian generalized probability calculus for density matrices

Machine Learning
Probabilistic principal component analysis based on Joystick probability selector
Modulated Hebb-Oja learning Rule-a method for principal subspace analysis

IEEE Transactions on Neural Networks

A new probabilistic approach to independent component analysis suitable for on-line learning in artificial neural networks

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we introduce elements of probabilistic model that is suitable for modeling of learning algorithms in biologically plausible artificial neural networks framework. Model is based on two of the main concepts in quantum physics - a density matrix and the Born rule. As an example, we show that proposed probabilistic interpretation is suitable for modeling of on-line learning algorithms for PSA, which are preferably realized by a parallel hardware based on very simple computational units. Proposed concept (model) can be used in the context of improving algorithm convergence speed, learning factor choice, or input signal scale robustness. We show how the Born rule and the Hebbian learning rule are connected.