Supervised Learning in Physical Networks: From Machine Learning to Learning Machines

Stern, Menachem; Hexner, Daniel; Rocks, Jason W.; Liu, Andrea J.

doi:10.1103/physrevx.11.021045

Cited by 52 publications

(82 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, metamaterials might yield physical realizations, with serially coupled mechanical hysterons naturally implementing antiferromagnetic interactions [27,31,33]. Finally, viscoelastic effects could be leveraged to obtain rate-dependent pathways and t-graphs and self-learning systems [36][37][38][39][40]. Together, progress on these questions will realize targeted pathways and information processing in designer materials.…”

Section: Discussionmentioning

confidence: 99%

Profusion of transition pathways for interacting hysterons

Hecke

2021

Phys. Rev. E

View full text Add to dashboard Cite

The response, pathways, and memory effects of cyclically driven complex media can be captured by hysteretic elements called hysterons. Here we demonstrate the profound impact of hysteron interactions on pathways and memory. Specifically, while the Preisach model of independent hysterons features a restricted class of pathways which always satisfy return point memory, we show that three interacting hysterons generate more than 15 000 transition graphs, with most violating return point memory and having features completely distinct from the Preisach model. Exploring these opens a route to designer pathways and information processing in complex matter.

show abstract

Section: Discussionmentioning

confidence: 99%

Profusion of transition pathways for interacting hysterons

Hecke

2021

Phys. Rev. E

View full text Add to dashboard Cite

show abstract

“…When a test set is given to the network to check its performance (by applying the input voltages appropriately) errors are calculated via the difference between the free state outputs and the desired outputs. A more detailed description of coupled learning is given in previous work [19].…”

Section: Coupled Learningmentioning

confidence: 99%

“…Coupled learning [19] is a theoretical framework specifying evolution equations that enable supervised, contrastive learning in physical networks. In the case of a resistor network, inputs and outputs are applied and measured voltages at nodes of the network, and the edges modify their resistance according to local rules.…”

Section: Coupled Learningmentioning

confidence: 99%

“…Thus, the output nodes are held at values closer to the desired outputs. When η 1 this algorithm approaches gradient descent [19]. This generates the 'clamped' response of the network.…”

Section: Coupled Learningmentioning

confidence: 99%

“…Recent work [18] has demonstrated the feasibility of entirely distributed, physics-driven learning in self-adjusting resistor networks. This system operates using Coupled Learning [19], a theoretical framework for training physical systems using local rules [20][21][22] and physical processes [23][24][25] in lieu of gradient descent and a central processor. Because of its distributed nature, this system scales in speed and efficiency far better than ANNs and is robust to damage, and may one day be a useful platform for machine learning applications, or robust smart sensors.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning Without a Global Clock: Asynchronous Learning in a Physics-Driven Learning Network

Wycoff,

Dillavou,

Stern

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

In a neuron network, synapses update individually using local information, allowing for entirely decentralized learning. In contrast, elements in an artificial neural network (ANN) are typically updated simultaneously using a central processor. Here we investigate the feasibility and effect of asynchronous learning in a recently introduced decentralized, physics-driven learning network. We show that desynchronizing the learning process does not degrade performance for a variety of tasks in an idealized simulation. In experiment, desynchronization actually improves performance by allowing the system to better explore the discretized state space of solutions. We draw an analogy between asynchronicity and mini-batching in stochastic gradient descent, and show that they have similar effects on the learning process. Desynchronizing the learning process establishes physics-driven learning networks as truly fully distributed learning machines, promoting better performance and scalability in deployment.

show abstract

Deep Learning in Mechanical Metamaterials: From Prediction and Generation to Inverse Design

et al. 2023

View full text Add to dashboard Cite

Mechanical metamaterials are meticulously designed structures with exceptional mechanical properties determined by their microstructures and constituent materials. Tailoring their material and geometric distribution unlocks the potential to achieve unprecedented bulk properties and functions. However, current mechanical metamaterial design considerably relies on experienced designers' inspiration through trial and error, while investigating their mechanical properties and responses entails time‐consuming mechanical testing or computationally expensive simulations. Nevertheless, recent advancements in deep learning have revolutionized the design process of mechanical metamaterials, enabling property prediction and geometry generation without prior knowledge. Furthermore, deep generative models can transform conventional forward design into inverse design. Many recent studies on the implementation of deep learning in mechanical metamaterials are highly specialized, and their pros and cons may not be immediately evident. This critical review provides a comprehensive overview of the capabilities of deep learning in property prediction, geometry generation, and inverse design of mechanical metamaterials. Additionally, this review highlights the potential of leveraging deep learning to create universally applicable datasets, intelligently designed metamaterials, and material intelligence. This article is expected to be valuable not only to researchers working on mechanical metamaterials but also those in the field of materials informatics.This article is protected by copyright. All rights reserved

show abstract

Supervised Learning in Physical Networks: From Machine Learning to Learning Machines

Cited by 52 publications

References 32 publications

Profusion of transition pathways for interacting hysterons

Profusion of transition pathways for interacting hysterons

Learning Without a Global Clock: Asynchronous Learning in a Physics-Driven Learning Network

Deep Learning in Mechanical Metamaterials: From Prediction and Generation to Inverse Design

Contact Info

Product

Resources

About