REVIEW 4 cited by
Physical networks become what they learn
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Physical networks can develop diverse responses, or functions, by design, evolution or learning. We focus on electrical networks of nodes connected by resistive edges. Such networks can learn by adapting edge conductances to lower a cost function that penalizes deviations from a desired response. The network must also satisfy Kirchhoff's law, balancing currents at nodes, or, equivalently, minimizing total power dissipation by adjusting node voltages. The adaptation is thus a double optimization process, in which a cost function is minimized with respect to conductances, while dissipated power is minimized with respect to node voltages. Here we study how this physical adaptation couples the cost landscape, the landscape of the cost function in the high-dimensional space of edge conductances, to the physical landscape, the dissipated power in the high-dimensional space of node voltages. We show how adaptation links the physical and cost Hessian matrices, suggesting that the physical response of networks to perturbations holds significant information about the functions to which they are adapted.
Forward citations
Cited by 4 Pith papers
-
On the rectification of oscillatory flows by flexible leaflets in a confined geometry
Collective flexible leaflets rectify low-Re oscillatory squeeze flow, maximizing net transport at high density and an optimal elastoviscous number η.
-
Thermally Robust Cooperative Function in Mechanical Networks
Symmetric training of mechanical networks produces cooperative binding, and a modified training that raises the frequency of the functional mode increases the temperature at which thermal fluctuations destroy that coo...
-
Large Interconnected Thermodynamic Systems Nearly Minimize Entropy Production
Numerical sampling of random nonequilibrium Markov chains shows steady-state entropy production approaching its minimum as the number of states grows.
-
Microscopic imprints of learned solutions in adaptive resistor networks
The susceptibility of edges in a trained resistor network contains all physical information of the cost landscape and identifies the edges responsible for the learned function.
Discussion (0). Continue with ORCID to comment.