Limits...
Structural drift: the population dynamics of sequential learning.

Crutchfield JP, Whalen S - PLoS Comput. Biol. (2012)

Bottom Line: We introduce a theory of sequential causal inference in which learners in a chain estimate a structural model from their upstream "teacher" and then pass samples from the model to their downstream "student".It extends the population dynamics of genetic drift, recasting Kimura's selectively neutral theory as a special case of a generalized drift process using structured populations with memory.We also demonstrate how the organization of drift process space controls fidelity, facilitates innovations, and leads to information loss in sequential learning with and without memory.

View Article: PubMed Central - PubMed

Affiliation: Complexity Sciences Center, Physics Department, University of California Davis, Davis, California, United States of America. chaos@ucdavis.edu

ABSTRACT
We introduce a theory of sequential causal inference in which learners in a chain estimate a structural model from their upstream "teacher" and then pass samples from the model to their downstream "student". It extends the population dynamics of genetic drift, recasting Kimura's selectively neutral theory as a special case of a generalized drift process using structured populations with memory. We examine the diffusion and fixation properties of several drift processes and propose applications to learning, inference, and evolution. We also demonstrate how the organization of drift process space controls fidelity, facilitates innovations, and leads to information loss in sequential learning with and without memory.

Show MeSH
-Machine for the Alternating Process consisting of two causal states  and two transitions.State  emits allele 0 with probability one and transitions to state , while  emits allele 1 with probability one and transitions to .
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3369870&req=5

pcbi-1002510-g002: -Machine for the Alternating Process consisting of two causal states and two transitions.State emits allele 0 with probability one and transitions to state , while emits allele 1 with probability one and transitions to .

Mentions: Consider a simple binary process that alternately generates s and s called the Alternating Process shown in Figure 2. Its -machine generates either the string or depending on the start state. The per-symbol transition matrices are:(8)(9)


Structural drift: the population dynamics of sequential learning.

Crutchfield JP, Whalen S - PLoS Comput. Biol. (2012)

-Machine for the Alternating Process consisting of two causal states  and two transitions.State  emits allele 0 with probability one and transitions to state , while  emits allele 1 with probability one and transitions to .
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3369870&req=5

pcbi-1002510-g002: -Machine for the Alternating Process consisting of two causal states and two transitions.State emits allele 0 with probability one and transitions to state , while emits allele 1 with probability one and transitions to .
Mentions: Consider a simple binary process that alternately generates s and s called the Alternating Process shown in Figure 2. Its -machine generates either the string or depending on the start state. The per-symbol transition matrices are:(8)(9)

Bottom Line: We introduce a theory of sequential causal inference in which learners in a chain estimate a structural model from their upstream "teacher" and then pass samples from the model to their downstream "student".It extends the population dynamics of genetic drift, recasting Kimura's selectively neutral theory as a special case of a generalized drift process using structured populations with memory.We also demonstrate how the organization of drift process space controls fidelity, facilitates innovations, and leads to information loss in sequential learning with and without memory.

View Article: PubMed Central - PubMed

Affiliation: Complexity Sciences Center, Physics Department, University of California Davis, Davis, California, United States of America. chaos@ucdavis.edu

ABSTRACT
We introduce a theory of sequential causal inference in which learners in a chain estimate a structural model from their upstream "teacher" and then pass samples from the model to their downstream "student". It extends the population dynamics of genetic drift, recasting Kimura's selectively neutral theory as a special case of a generalized drift process using structured populations with memory. We examine the diffusion and fixation properties of several drift processes and propose applications to learning, inference, and evolution. We also demonstrate how the organization of drift process space controls fidelity, facilitates innovations, and leads to information loss in sequential learning with and without memory.

Show MeSH