Bayesianism without learning
نویسنده
چکیده
According to the standard definition, a Bayesian agent is one who forms his posterior belief by conditioning his prior belief on what he has learned, that is, on facts of which he has become certain. Here it is shown that Bayesianism can be described without assuming that the agent acquires any certain information; an agent is Bayesian if his prior, when conditioned on his posterior belief, agrees with the latter. This condition is shown to characterize Bayesian models. 1999 Academic Press
منابع مشابه
Bayesianism and Information
Bayesianism is a theory of inductive inference that makes use of the mathematical theory of probability. Bayesians usually hold that the relevant probabilities should be interpreted in terms of rational degrees of belief. This still leaves much scope for disagreement, since there is no consensus about what norms govern rational degrees of belief. In this chapter, we first provide an introductio...
متن کاملBayesianism as a Whole
The current paper provides an overview of Bayesian techniques applied to frequently appearing issues in the field of Artificial Intelligence. It covers design of belief systems, reasoning under uncertainty, use in advanced learning systems such as Bayesian Problem Learning and application to various fields. Lastly it touches limitation and disadvantages of such approaches to discussed problems.
متن کاملLocating IBE in the Bayesian framework
Inference to the Best Explanation (IBE) and Bayesianism are our two most prominent theories of scientific inference. Are they compatible? Van Fraassen famously argued that they are not, concluding that IBE must be wrong since Bayesianism is right. Writers since then, from both the Bayesian and explanationist camps, have usually considered van Fraassen’s argument to be misguided, and have plumpe...
متن کاملProbabilistic Sophistication and Reverse Bayesianism
This paper extends our earlier work on reverse Bayesianism by relaxing the assumption that decision makers abide by expected utility theory, assuming instead weaker axioms that merely imply that they are probabilistically sophisticated. We show that our main results, namely, (modified) representation theorems and corresponding rules for updating beliefs over expanding state spaces and null even...
متن کاملAdaptive learning via selectionism and Bayesianism, Part I: Connection between the two
According to the selection-by-consequence characterization of operant learning, individual animals/species increase or decrease their future probability of action choices based on the consequence (i.e., reward or punishment) of the currently selected action (the so-called "Law of Effect"). Under Bayesianism, on the other hand, evidence is evaluated based on likelihood functions so that action p...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1999