Computer Science – Learning
Scientific paper
2004-06-06
pp. 504--511 in Max Chickering and Joseph Halpern (eds.), _Uncertainty in Artificial Intelligence: Proceedings of the Twentiet
Computer Science
Learning
8 pages, 4 figures
Scientific paper
We present a new method for nonlinear prediction of discrete random sequences under minimal structural assumptions. We give a mathematical construction for optimal predictors of such processes, in the form of hidden Markov models. We then describe an algorithm, CSSR (Causal-State Splitting Reconstruction), which approximates the ideal predictor from data. We discuss the reliability of CSSR, its data requirements, and its performance in simulations. Finally, we compare our approach to existing methods using variable-length Markov models and cross-validated hidden Markov models, and show theoretically and experimentally that our method delivers results superior to the former and at least comparable to the latter.
Shalizi Cosma Rohilla
Shalizi Kristina Lisa
No associations
LandOfFree
Blind Construction of Optimal Nonlinear Recursive Predictors for Discrete Sequences does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Blind Construction of Optimal Nonlinear Recursive Predictors for Discrete Sequences, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Blind Construction of Optimal Nonlinear Recursive Predictors for Discrete Sequences will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-382226