Skip to content
Preprint

Learning constructive models of emergent systems

Aug 2026 · 0 citations
Physics Biology

TL;DR

It is shown that inferring scales of system entropy then constraining information from low to high entropic scales yields stepwise constructive models, called the Layer-Restricted Boltzmann Machine (LRBM), which demonstrates a shared, learnable logic for constructing emergent systems.

Abstract

Emergent systems - systems with multiscale interactions - arise through iteration than forward design, leaving principles for building them under-explored. Current artificial intelligence architectures, while useful for generation, provide no logic for construction. Inspired by statistical phylogenetics, we show that inferring scales of system entropy then constraining information from low to high entropic scales yields stepwise constructive models. We term this architecture the Layer-Restricted Boltzmann Machine (LRBM). Applied identically to digit images, natural language, and enzyme sequences, LRBMs follow a common hierarchical logic: lower layers encode global structure, higher layers fine-grained features. As a stringent test, we assayed 160 synthetic chorismate mutase (CM) constructive trajectories alongside 1,130 natural homologs in vivo. Designed CMs functioned up to 53% divergent from nearest natural homolog. Fold emerged at intermediate layers while function required all layers, illustrating that fold was necessary but insufficient for function. Our results demonstrate a shared, learnable logic for constructing emergent systems.

View source

Similar papers

Preprint Aug 2026

Emergent Models: Intelligence from Tiny Substrates

Emergent Models (EMs) are a machine learning paradigm based on simple yet open-ended substrates, such as cellular automata, in which modeling is treated not as the learning of a closed-form input-output map but as the emergence, within simple dynamical systems, of computational behaviors that solve external tasks. Such...

Giacomo Bocchese, Nicola Giacobbo, Etienne Guichard et al. · 0 citations
Preprint Sep 2026

The Computational Primitives of Adaptation

It is proposed that adaptation has its own computational structure, comprising a small set of primitive operations common to all adaptive systems, regardless of their physical form, and these primitives must be implemented if the systems are to be adaptive.

J. W. Page · 0 citations
Open access Aug 2026

PatternFormer: Learning Multiple Solution Patterns in Reaction--Diffusion Systems

PatternFormer is developed, a large language model-based framework for learning the multiple solutions of nonlinear partial differential equations that produces structured solution sets in a single autoregressive pass, terminating automatically for finite families and enforcing physical residual constraints for unbound...

Wenrui Hao, Zhipeng Chang, Wen-Peng Yin · 0 citations
Preprint Aug 2026

Convergent Evolution in Algorithmic Space

In evolutionary biology, unrelated organisms can independently evolve similar structures when exposed to similar functional demands. Here we ask whether an analogous form of convergent evolution occurs during neural network training: do networks with different random initializations develop similar internal weight stru...

Patrick Krauss, Achim Schilling, Andreas K. Maier et al. · 1 citation
#artificial intelligence Preprint Sep 2026

T-GADE: Thermodynamical Generative-AI-Driven Evolution of LLM Artifacts

The utility of thermodynamical selection and validation-based use of retained artifacts are demonstrated, and T-GADE is proposed, which evolves these artifacts by extending thermodynamical genetic algorithms through LLM-based genetic operators and artifact-level diversity evaluation.

Kyoko Ogawa, N. Mori · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.