claim

active

claim:by-using-a-variational-autoencoder-like-architecture-for-genomic-compression-evolution-is-freed-from-over-training-and-pushed-to-evolve-general-purpose-problem-solving-machines

By using a variational autoencoder-like architecture for genomic compression, evolution is freed from over-training and pushed to evolve general-purpose problem-solving machines.

Claim linking the indirect genotype-phenotype mapping to robustness and open-endedness.

Source paper

extracted_from

Darwin's agential materials: evolutionary implications of multiscale competency in developmental biology

(2023) · Levin, Michael

Neighborhood — ranked by edge-count

Communities (2)

community

Causal emergence in biological systems
members_of
Examines how macro-scale causal power exceeds micro-scale in living and learning systems.
Agential evolution & biological individuality
members_of
Frames evolution as producing goal-directed, problem-solving agents across nested scales of individuality.

Claims (1)

claim

Evolution actually searches not only genotype space but a more tractable space of behavior-shaping signals that exploit cellular intelligence.
extends
Central thesis of the paper.

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.

Autoencoder-like compression forces evolution of general-purpose problem-solving machines with inherent robustnesshypothesis0.831
Evolution learns to generalize beyond default morphologies, producing problem-solving machines.claim0.806
Argues that evolutionary learning goes beyond specific adaptations.
Evolution often produces general-purpose problem-solving machines whose capacities cannot be inferred from the default invariant course of development.claim0.800
A claim about the outcome of the MCA-enhanced process.
Evolution does not simply make hardwired machines that execute a predetermined set of steps; instead, it produces problem-solving hardware.claim0.798
Key insight about the nature of evolved systems.
The key to the idea that will allow a system of workable morphogenetic sequences to evolve in a not-too great length of time, is highlighted in the genetic ideas of John Holland.quote0.771
Explicitly credits Holland's work as the inspiration for the snippable genes approach.
Autoencoder Architecture (Variational)framework0.771
A machine-learning analogy: evolution learns both an encoding (genome compression) and a decoder (morphogenetic process); explains how evolution avoids overfitting and evolves general-purpose problem-solving.
Keeping goal state encodings functionally orthogonal from the machinery that executes them (as in bioelectric pattern memories) is a powerful architecture exploited by evolution.claim0.766
Argues this separation allows reprogramming without hardware change.
The multiscale competency architecture (MCA) speeds evolutionary search by providing generalization, reliability, tractable search space, cryptic variation, and functional intermediates.claim0.765
Main functional claim about MCA.