4 April 1997 High-order polytomous Boltzmann machine and forecasting time series I
Author Affiliations +
Abstract
We use the polytomous Boltzmann Machine for time series forecasting and prediction applications. We will simulate the polytomous Boltzmann Machine by using the binary Boltzmann Machine. We will show our software (1) can learn and predict the behavior of deterministic dynamic systems. Given enough training, the software can predict with 100% accuracy; (2) can learn and predict the behavior of the Markov chains (or probabilistic finite state machines). Given enough training, the software can predict with 100% accuracy.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ying Liu, Ying Liu, } "High-order polytomous Boltzmann machine and forecasting time series I", Proc. SPIE 3077, Applications and Science of Artificial Neural Networks III, (4 April 1997); doi: 10.1117/12.271502; https://doi.org/10.1117/12.271502
PROCEEDINGS
13 PAGES


SHARE
RELATED CONTENT

The beta-alpha-encoders for A/D conversion
Proceedings of SPIE (September 26 2007)
N dimension geometry used in the design of a dynamic...
Proceedings of SPIE (January 18 2009)
Use of chaos to generate broadband signals
Proceedings of SPIE (June 30 1999)
Continuous-tone image recognition using fractal theory
Proceedings of SPIE (November 30 1993)
Closer look at mutation in genetic algorithms
Proceedings of SPIE (October 28 1993)

Back to Top