Trade-off among parameters affecting inductive inference

Optimizing the quantity/quality trade-off in connectome inference

We demonstrate a meaningful prospective power analysis for an (admittedly idealized) illustrative connectome inference task. Modeling neurons as vertices and synapses as edges in a simple random graph model, we optimize the trade-off between the number of (putative) edges identified and the accuracy of the edge identification procedure. We conclude that explicit analysis of the quantity/quality...

Inductive Inference

Fixed Parameter Inductive Inference

We investigate a particular inductive inference problem where we are given as input a finite set of ordered triples of the form (wi, bi, ti) such that wi is a bit string, bi is a single bit, and ti is a positive integer written in unary. A machine M is said to match such a triple if M outputs bi on input wi in at most ti steps. We proceed to investigate the fixed parameter problems where we fix...

Statistics as Inductive Inference

This chapter concerns the relation between statistics and inductive logic. I start by describing induction in formal terms, and I introduce a general notion of probabilistic inductive inference. This provides a setting in which statistical procedures and inductive logics can be captured. Specifically, I discuss three statistical procedures (hypotheses testing, parameter estimation, and Bayesian...

Communication of inductive inference

This proposal is primarily aimed at the third group of agent systems. In addition to the study of the design of individual agents and communities, recent work has focused on allowing diverse agents and communities to interoperate. This is the goal of the Knowledge Sharing Effort [KSE] (Patil et.al., 1992). The Knowledge Query and Manipulation Language [KQML] (Finin et.al., 1993) is the componen...