Corpus ID: 5416472

Beyond Almost-Sure Termination

@article{Icard2017BeyondAT,
  title={Beyond Almost-Sure Termination},
  author={Thomas F. Icard},
  journal={Cognitive Science},
  year={2017}
}
The aim of this paper is to argue that models in cognitive science based on probabilistic computation should not be restricted to those procedures that almost surely (with probability 1) terminate. There are several reasons to consider nonterminating procedures as candidate components of cognitive models. One theoretical reason is that there is a perfect correspondence between the enumerable semi-measures and all probabilistic programs, as we demonstrate here (generalizing a better-known fact… Expand
Weakest Preexpectation Semantics for Bayesian Inference
Causal Modeling with Probabilistic Simulation Models
From Programs to Causal Models ∗

References

SHOWING 1-10 OF 25 REFERENCES
On the Hardness of Almost-Sure Termination
Towards common-sense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence
Solomonoff Prediction and Occam’s Razor
Probabilistic operational semantics for the lambda calculus
Noncomputable Conditional Distributions
Probabilistic Program Analysis with Martingales
Stimulus-response theory of finite automata
The logical primitives of thought: Empirical foundations for compositional cognitive models.
The Generalized Universal Law of Generalization
Church: a language for generative models
...
1
2
3
...