Prediction using unsupervised learning

DOI10.1016/0167-2789(93)90203-DzbMath0786.92001MaRDI QIDQ1312510

V. Pereyra

Publication date: 15 May 1994

Published in: Physica D (Search for Journal in Brave)

zbMATH Keywords

prediction error; time series; connectivity; learning process; competitive learning; unsupervised learning; information entropy; network size; intrinsic properties; dynamical clustering; scaling behaviour; coarse-grained dynamics; dynamics of nonlinear dissipative systems; long-term regularities; master equation approach; simulations of discrete mapping

Mathematics Subject Classification ID

92B20: Neural networks for/in biological studies, artificial life and related topics

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The infinite number of generalized dimensions of fractals and strange attractors
• The universal metric properties of nonlinear transformations
• A two-dimensional mapping with a strange attractor
• Dimensions and entropies of strange attractors from a fluctuating dynamics approach
• Kalman filtering with real-time applications
• Nonlinear prediction of chaotic time series
• Neocognition: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position
• State space reconstruction in the presence of noise
• Neural theory of association and concept-formation
• Quantitative universality for a class of nonlinear transformations
• Ergodic theory of chaos and strange attractors