finding

active

finding:folding-pathways-of-creased-sheets-can-be-trained-for-specific-topologies-including-classification-of-mechanical-force-patterns-analogous-to-neural-networks

Folding pathways of creased sheets can be trained for specific topologies including classification of mechanical force patterns analogous to neural networks

Experimentally validated finding that origami/kirigami systems can solve classification tasks through physical learning of crease stiffnesses

Source paper

extracted_from

Learning without neurons in physical systems

(2022) · Menachem Stern · Arvind Murugan

Neighborhood — ranked by edge-count

Claims (1)

claim

Physical systems are more constrained in learning abilities than in silico neural networks due to locality requirements, but this mirrors biological learning constraints and offers robustness benefits
supports
Core theoretical claim establishing that locality constraints in physical learning are not fatal—they reflect biological precedent and provide advantages like robustness and scalability

Communities (2)

community

Causal emergence in biological systems
members_of
Examines how macro-scale causal power exceeds micro-scale in living and learning systems.
Multi-scale credit assignment in evolutionary systems
members_of
Hierarchical competency architectures that improve evolutionary learning by linking actions to rewards across temporal and spatial scales, enabling faster convergence and generalization.

Concepts (1)

concept

Origami and Kirigami sheets
supports
2D sheets with crease patterns that fold into specific topologies; learning d.o.f include crease bending stiffness; can be trained for classification tasks

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.

In nature, unfolding often consists of a process that establishes local symmetries one by one.claim0.761
Connects biological morphogenesis to architectural process.
Free-energy scaling under domain-wall formation in Potts, autoregressive, and hierarchical networks shows that combinatorics of interactions on a graph prevent or allow spontaneous ordering.finding0.739
Core result demonstrating topological constraints on self-organization
Neural networks compute cyclic concepts in generic substrate machinery (base-10 addition) not naturally cyclic computation.claim0.738
Olah et al. (2020) found that automatically trained computer vision models, regardless of architecture and training procedure, all arrive at similar functional structures organizing similar features into similar compositional hierarchies, closely resembling the primate visual cortex.finding0.736
Empirical finding supporting the Universality Hypothesis; extended by the paper to consciousness
Simple, intentionally rough paper and cardboard models that can be rapidly torn, cut, and patched provide a practical way to evolve design through feedback.claim0.733
Proposed practical method for achieving step-by-step feedback in design.
We hypothesize that a similar 'brutal' and purely geometric process always occurs somewhere in other kinds of unfolding that generate living order — in poetry, dance, social structure, planning, and family relationships.hypothesis0.729
Extends the brutal geometry thesis beyond architecture into all creative and social domains; acknowledged as not yet confirmed with certainty
The practical crux of unfolding, the essence of every living process, is that it is above all a GEOMETRIC process.claim0.726
Alexander's emphasis that even loose, organic forms arise from geometric transformations.
What Mechanisms Scale Celllevel Feedback Loops Into Anatomicalquestion0.725