claim

active

claim:a-connectionist-approach-resolves-the-chicken-and-egg-problem-of-etis-by-focusing-on-the-changing-organisation-of-relationships-between-lower-level-units-not-unit-frequencies

A connectionist approach resolves the chicken-and-egg problem of ETIs by focusing on the changing organisation of relationships between lower-level units, not unit frequencies

The paper's proposed solution

Source paper

extracted_from

Design for an Individual: Connectionist Approaches to the Evolutionary Transitions in Individuality

(2022) · Watson, Richard A. · Levin, Michael · Buckley, Christopher L.

Neighborhood — ranked by edge-count

Findings (1)

finding

Power's ecosystem model with individual-level selection on interaction traits evolves to solve Sudoku puzzles (Power 2019)
supports
Demonstrates that ecological networks can learn complex problem-solving without system-level selection

Questions (1)

question

How do they come to work together in this way?
gates
Earlier framing question

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

The application of connectionist models also extends into the domain of evolutionary systems, where the connections of a network are changed by variation and selection.claim0.781
Formal equivalence between evolutionary variation/selection and connectionist learning.
Chicken-and-Egg Problem of ETIsquestion0.777
Conventional evolutionary framework cannot explain adaptations in systems that are not already evolutionary units, creating a chicken-and-egg problem for ETIsclaim0.777
Central critique of existing theory, motivating the connectionist alternative
ETIs are the evolutionary equivalent of deep learning: (i) required functional relationships encode non-decomposable functions, (ii) these are enacted by basal cognition mechanisms, and (iii) conditions for deep model induction predict ETI occurrence.hypothesis0.776
Overarching three-part hypothesis stated in introduction
H2: The conditions necessary for the induction of deep models, familiar in connectionist models of learning and cognition, are predictive of the conditions necessary for an ETI to occur.hypothesis0.768
Second hypothesis linking learning theory directly to evolutionary transitions
Connectionist learning principles apply equally to evolutionary systems where variation and selection alter network organization, instantiating distributed learning at evolutionary timescales.hypothesis0.762
Connectionist Approach To Evolutionary Transitions In Individualityframework0.761
Connectionist models of cognition and learning identify conditions where collective intelligence can arise bottom-up, using only distributed learning mechanisms without system-level or global feedback.claim0.761
Central claim about the power of connectionism.