Learning to self-fold at a bifurcation

Arinze, Chukwunonso; Stern, Menachem; Nagel, Sidney R.; Murugan, Arvind

doi:10.1103/physreve.107.025001

Cited by 8 publications

(2 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[46][47][48] Recently, employing potential energies of the two states of the system as the two different inputs, contrastive Hebbian learning has inspired the development of completely distributed and physics-driven learning machines. [49][50][51][52][53] In those designs, learning degrees of freedom are updated based on only local conditions. Consequently, the method can be more scalable The active bond contains a strain sensor, a controller, and an actuating element that modulates the stiffness of the bond.…”

Section: Introductionmentioning

confidence: 99%

Learning Stiffness Tensors in Self‐Activated Solids via a Local Rule

Tang,

Ye,

Jia

et al. 2024

Advanced Science

View full text Add to dashboard Cite

Mechanical metamaterials are often designed with particular properties for specific load‐bearing functions. Alternatively, this study aims to create a class of active lattice metamaterials, dubbed self‐activated solids, that can learn desired stiffness tensors from the elastic deformations they experienced, a crucial feature to improve the performance, efficiency, and functionality of materials. Artificial adaptive matters that combine sensory, control, and actuation elements can offer appealing solutions. However, challenges still remain: The designs will rely on accurate off‐line and global computations, as well as intricate coordination among individual elements. Here, a simple online and local learning strategy is initiated based on contrastive Hebbian learning to gradually guide self‐activated solids to possess sought‐after stiffness tensors autonomously and reversibly. During learning, the bond stiffness of the active lattice varies depending only on its local strain. The numerical tests show that the self‐activated solid can not only achieve the desired bulk, shear, and coupling moduli but also manifest uni‐mode and bi‐mode extremal materials by itself after experiencing the corresponding elastic deformations. Further, the self‐activated solid can also achieve the desired time‐varying moduli when exposed to temporally different loads. The design is applicable to any lattice geometries and is resistant to damage and instabilities. The material design approach and the physical learning strategy suggested can benefit the design of autonomous materials, physical learning machines, and adaptive robots.

show abstract

Section: Introductionmentioning

confidence: 99%

Learning Stiffness Tensors in Self‐Activated Solids via a Local Rule

Tang,

Ye,

Jia

et al. 2024

Advanced Science

View full text Add to dashboard Cite

show abstract

“…Local rules have also been exploited to train laboratory non-biological mechanical networks to exhibit auxetic behavior [8,9] or proteininspired functions [10][11][12]. Other local rules have been proposed for associative memory [13][14][15][16][17]; one of them has even been demonstrated in the lab [18]. Here we will focus on a powerful set of local rules based on the framework of Contrastive Hebbian Learning, which perform approximate gradient descent of a cost function [19][20][21][22][23][24][25][26].…”

Section: Introductionmentioning

confidence: 99%

The Physical Effects of Learning

Stern

Liu

Balasubramanian

2023

Preprint

Self Cite

View full text Add to dashboard Cite

Interacting many-body physical systems ranging from neural networks in the brain to folding proteins to self-modifying electrical circuits can learn to perform specific tasks. This learning, both in nature and in engineered systems, can occur through evolutionary selection or through dynamical rules that drive active learning from experience. Here, we show that learning leaves architectural imprints on the Hessian of a physical system. Compared to a generic organization of the system components, (a) the effective physical dimension of the response to inputs (the participation ratio of low-eigenvalue modes) decreases, (b) the response of physical degrees of freedom to random perturbations (or system ``susceptibility'') increases, and (c) the low-eigenvalue eigenvectors of the Hessian align with the task. Overall, these effects suggest a method for discovering the task that a physical network may have been trained for.

show abstract