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

Related in: MedlinePlus

Drift of allelic entropy  and Pr[Heads] for a single realization of the Biased Coin Process with sample size .The drift of Pr[Heads] is annotated with its initial machine  (left inset) and the machine at stasis  (right inset).
© Copyright Policy
Related In: Results  -  Collection

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

pcbi-1002510-g006: Drift of allelic entropy and Pr[Heads] for a single realization of the Biased Coin Process with sample size .The drift of Pr[Heads] is annotated with its initial machine (left inset) and the machine at stasis (right inset).

Mentions: Figure 6 shows structural drift, using two different measures, for a single realization of the Biased Coin Process with initial [Heads] = Pr [Tails] = 0.5. Structural stasis () is reached after generations. The initial Fair Coin -machine occurs at the left of Figure 6 and the final, completely biased -machine occurs at the right.


Structural drift: the population dynamics of sequential learning.

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

Drift of allelic entropy  and Pr[Heads] for a single realization of the Biased Coin Process with sample size .The drift of Pr[Heads] is annotated with its initial machine  (left inset) and the machine at stasis  (right inset).
© Copyright Policy
Related In: Results  -  Collection

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

pcbi-1002510-g006: Drift of allelic entropy and Pr[Heads] for a single realization of the Biased Coin Process with sample size .The drift of Pr[Heads] is annotated with its initial machine (left inset) and the machine at stasis (right inset).
Mentions: Figure 6 shows structural drift, using two different measures, for a single realization of the Biased Coin Process with initial [Heads] = Pr [Tails] = 0.5. Structural stasis () is reached after generations. The initial Fair Coin -machine occurs at the left of Figure 6 and the final, completely biased -machine occurs at the right.

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
Related in: MedlinePlus