claim

active

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

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

Core theoretical claim establishing that locality constraints in physical learning are not fatal—they reflect biological precedent and provide advantages like robustness and scalability

Source paper

extracted_from

Learning without neurons in physical systems

(2022) · Menachem Stern · Arvind Murugan

Neighborhood — ranked by edge-count

Findings (1)

finding

Folding pathways of creased sheets can be trained for specific topologies including classification of mechanical force patterns analogous to neural networks
supports
Experimentally validated finding that origami/kirigami systems can solve classification tasks through physical learning of crease stiffnesses

Communities (3)

community

Causal emergence in biological systems
members_of
Examines how macro-scale causal power exceeds micro-scale in living and learning systems.
Bioelectric morphogenesis & memory
members_of
Michael Levin's research on bioelectric signaling controlling anatomical goals, regeneration, and cancer.
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.

Questions (1)

question

To what extent can physical systems learn by exploiting typically local natural processes without any explicit cost function?
gates
Central research question defining the scope of physical learning; asks about achievable learning under locality constraints

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.

Neural bioelectric networks achieve a critical separation of hardware and software: the same molecular substrate can instantiate different informational content based on history, enabling minds to arise from matter.claim0.796
Foundational for understanding how physiology becomes meaning; decoupling of material state from information content is prerequisite for emergence of cognitive Self.
Learning neural networks can enable 'chunking' and rescale problem-solving to higher organizational levels, a mechanism intrinsic to transitions in individuality.hypothesis0.795
What makes learning systems smart is that the parameters they adjust and the data to which they fit are not in the same space.claim0.793
Distillation of why learning generalises.
Bioelectric networks, with their inherent plasticity, multiscale historicity, and learning capacity, are an ideal kind of 'cognitive glue' that binds the primitive goal-directedness of single cells into a higher order system.concept0.792
Canonical definition of the paper's central concept; encapsulates mechanism of cognitive scaling through bioelectric integration.
Reinforcement learning acting on individual characteristics affecting their connections to others can result in dynamics that are equivalent to unsupervised learning at the system scale.claim0.788
Key insight linking individual rewards to system-level learning.
Self-similarity and multi-scale competency currently remain a real feature that distinguishes living systems from machines, though there is no deep reason preventing engineered artifacts from exploiting it.claim0.788
The one property the authors acknowledge still distinguishes life from machines, but frame as contingent not essential
A physical learning system thus has the following ingredients: Physical d.o.f s that respond to external stimuli f by adopting a state or dynamic behavior s(f), a subset of which defines the desired behavior (i.e., output); Learning d.o.f wi that can modify how the physical d.o.f s(f; {wi}) respond to external stimuli f; A learning rule, dwi = h(s(f; {wi}))dt, that modifies the learning d.o.f wi based on the response of the physical d.o.f s to the stimuli f.quote0.787
Foundational definition of physical learning system components; load-bearing for understanding the entire framework
Neural networks show substantial alignment with biological representations in the brain, driven by shared task and data constraintsclaim0.786
Extends convergence argument to brain-machine alignment