Elastic networks

Spring networks and mechanical systems used to demonstrate physical learning through modifications of bond stiffnesses in response to strain

Neighborhood — ranked by edge-count

paper

framework

Physical learning
associated_with
Framework for solving inverse problems in which physical systems autonomously adapt their parameters in response to stimuli through local learning rules, without requiring computational design or explicit cost functions

concept

Auxetic materials
associated_with
Materials with negative Poisson's ratio that contract laterally when stretched; trained through physical learning by imposing desired deformation

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 Networksconcept0.777
Flow networksconcept0.776
Networks for transport via fluid flow (biological vascular, engineered microfluidic); pipe properties adapt locally to control flow conductance and enable learning
Bioelectric Networksframework0.775
Ancient mechanism using ion channels, gap junctions, and neurotransmitters as 'cognitive glue' enabling collective intelligence across morphogenesis and behavior.
Cross-stitch networksmethod0.760
MTL architecture with linear combinations of activations across tasks.
Highway Networksconcept0.757
Early Schmidhuber group architecture using residual connections, precursor to the residual stream structure in transformers
Recurrent networksconcept0.753
Networks with loop connections that can maintain internal state and exhibit dynamical attractors.
Feed-forward networksconcept0.741
Networks without feedback loops, such as the Perceptron; limited to linearly separable functions.
Bioelectric Gene Networksframework0.731