Continual Learning of Multiple Memories in Mechanical Networks

Stern, Menachem; Pinson, Matthew B.; Murugan, Arvind

doi:10.1103/physrevx.10.031044

Cited by 30 publications

(28 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this argument, the cytoskeleton may undergo large structural changes in response to small changes in the relevant mechanical or chemical signals, an amplification that would serve to enhance cellular sensitivity during dynamic processes, such as chemotaxis. This could also enhance mechanical adaptivity, an increasingly well-documented feature of cytoskeletal networks ( 19 , 74 – 76 ). This connection between large cytoskeletal fluctuations and large susceptibility remains speculative at this stage, however, and would benefit from dedicated study.…”

Section: Discussionmentioning

confidence: 99%

Understanding cytoskeletal avalanches using mechanical stability analysis

Floyd

Levine

Jarzynski

et al. 2021

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

Eukaryotic cells are mechanically supported by a polymer network called the cytoskeleton, which consumes chemical energy to dynamically remodel its structure. Recent experiments in vivo have revealed that this remodeling occasionally happens through anomalously large displacements, reminiscent of earthquakes or avalanches. These cytoskeletal avalanches might indicate that the cytoskeleton’s structural response to a changing cellular environment is highly sensitive, and they are therefore of significant biological interest. However, the physics underlying “cytoquakes” is poorly understood. Here, we use agent-based simulations of cytoskeletal self-organization to study fluctuations in the network’s mechanical energy. We robustly observe non-Gaussian statistics and asymmetrically large rates of energy release compared to accumulation in a minimal cytoskeletal model. The large events of energy release are found to correlate with large, collective displacements of the cytoskeletal filaments. We also find that the changes in the localization of tension and the projections of the network motion onto the vibrational normal modes are asymmetrically distributed for energy release and accumulation. These results imply an avalanche-like process of slow energy storage punctuated by fast, large events of energy release involving a collective network rearrangement. We further show that mechanical instability precedes cytoquake occurrence through a machine-learning model that dynamically forecasts cytoquakes using the vibrational spectrum as input. Our results provide a connection between the cytoquake phenomenon and the network’s mechanical energy and can help guide future investigations of the cytoskeleton’s structural susceptibility.

show abstract

Section: Discussionmentioning

confidence: 99%

Understanding cytoskeletal avalanches using mechanical stability analysis

Floyd

Levine

Jarzynski

et al. 2021

Proc. Natl. Acad. Sci. U.S.A.

View full text Add to dashboard Cite

show abstract

“…Learning is a special case of memory [4,5], where the goal is to encode targeted functional responses in a network [6][7][8][9]. Artificial Neural Networks (ANNs) are complex functions designed to achieve such targeted responses.…”

Section: Introductionmentioning

confidence: 99%

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

“…Here we follow a different approach to learning that exploits physical processes, involving simple and local rules, in lieu of complex ones inspired by neurons or non-local computer science algorithms. In previous work, simulated and laboratory mechanical networks, and simulated flow networks, have been trained to perform desired tasks by adjusting their internal degrees of freedom [26][27][28][29][30][31][32][33][34][35][36][37][38][39]. This has been accomplished either by minimizing a global cost function [26][27][28][29][30] or using local rules [31][32][33][34][35][36][37][38][39], in which each edge of the network adjusts some property -such as its mechanical stiffness -that we will refer to as a 'learning degree of freedom' in response to the stress on it.…”

Section: Introductionmentioning

confidence: 99%

Demonstration of Decentralized, Physics-Driven Learning

Dillavou,

Stern,

Liu

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The brain is a physical system capable of producing immensely complex collective properties on demand. Unlike a typical man-made computer, which is limited by the bottleneck of one or more central processors, self-adjusting elements of the brain (neurons and synapses) operate entirely in parallel. Here we report laboratory demonstration of a new kind of physics-driven learning network comprised of identical self-adjusting variable resistors. Our system is a realization of coupled learning, a recently-introduced theoretical framework specifying properties that enable adaptive learning in physical networks. The inputs are electrical stimuli and physics performs the output 'computations' through the natural tendency to minimize energy dissipation across the system. Thus the outputs are analog physical responses to the input stimuli, rather than digital computations of a central processor. When exposed to training data, each edge of the network adjusts its own resistance in parallel using only local information, effectively training itself to generate the desired output. Our physical learning machine learns a range of tasks, including regression and classification, and switches between them on demand. It operates using well-understood physical principles and is made using standard, commercially available electronic components. As a result our system is massively scalable and amenable to theoretical understanding, combining the simplicity of artificial neural networks with the distributed parallel computation and robustness to damage boasted by biological neuron networks.

show abstract

Continual Learning of Multiple Memories in Mechanical Networks

Cited by 30 publications

References 46 publications

Understanding cytoskeletal avalanches using mechanical stability analysis

Understanding cytoskeletal avalanches using mechanical stability analysis

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

Demonstration of Decentralized, Physics-Driven Learning

Contact Info

Product

Resources

About