Learning Probabilistic Prediction Functions (Extended Abstract)

The question of how to learn rules, when those rules make probabilistic statements about the future, is considered. Issues are discussed that arise when attempting to determine what a good prediction function is, when those prediction functions make probabilistic assumptions. Learning has at least two purposes: to enable the learner to make predictions in the future and to satisfy intellectual curiosity as to the underlying cause of a process. Two results related to these distinct goals are given. In both cases, the inputs are a countable collection of functions which make probabilistic statements about a sequence of events. One of the results shows how to find one of the functions, which generated the sequence, the other result allows to do as well in terms of predicting events as the best of the collection. In both cases the results are obtained by evaluating a function based on a tradeoff between its simplicity and the accuracy of its predictions. >

Authors

• Alfredo De Santis
• George Markowsky
• Mark N. Wegman

Keywords

• Physics
• Time measurement
• Computer science
• Gaussian distribution
• Humans
• Gold
• Concrete
• Function Prediction
• Probability Function
• Infinity
• Markov Chain
• Set Of Functions
• Results Of This Paper
• Transition Probabilities
• Sequence Elements
• Sequence Position
• Elements
• Inductive Reasoning
• Automata
• Head And Tail
• Network Infrastructure
• Probability 1
• Starting State
• Pair Of States
• Deductive Reasoning
• Rational Numbers
• Infinite Sequence