REVIEW 8 cited by
Training of Physical Neural Networks
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 neural networks (PNNs) are a class of neural-like networks that leverage the properties of physical systems to perform computation. While PNNs are so far a niche research area with small-scale laboratory demonstrations, they are arguably one of the most underappreciated important opportunities in modern AI. Could we train AI models 1000x larger than current ones? Could we do this and also have them perform inference locally and privately on edge devices, such as smartphones or sensors? Research over the past few years has shown that the answer to all these questions is likely "yes, with enough research": PNNs could one day radically change what is possible and practical for AI systems. To do this will however require rethinking both how AI models work, and how they are trained - primarily by considering the problems through the constraints of the underlying hardware physics. To train PNNs at large scale, many methods including backpropagation-based and backpropagation-free approaches are now being explored. These methods have various trade-offs, and so far no method has been shown to scale to the same scale and performance as the backpropagation algorithm widely used in deep learning today. However, this is rapidly changing, and a diverse ecosystem of training techniques provides clues for how PNNs may one day be utilized to create both more efficient realizations of current-scale AI models, and to enable unprecedented-scale models.
Forward citations
Cited by 8 Pith papers
-
Coherent-State Propagation: A Computational Framework for Simulating Bosonic Quantum Systems
Coherent-state propagation enables quasi-polynomial classical simulation of bosonic circuits with logarithmically many Kerr gates at exponentially small trace-distance error, with polynomial runtime in the weak-nonlin...
-
Universality of physical neural networks with multivariate nonlinearity
A physical neural network is universal exactly when its multivariate nonlinear encoding function has no identically vanishing partial derivative.
-
Sequential Learning and Catastrophic Forgetting in Differentiable Resistor Networks
Differentiable resistor networks exhibit catastrophic forgetting in sequential learning, with forgetting severity tied to task conflict, adaptation degree, and network topology.
-
Non-Volatile Vortex MTJs with Opto-Electrical and Spin-Diode Nonlinearities as Multifunctional Neuromorphic Platforms
Vortex MTJs integrate non-volatile storage and cubic nonlinear response via bTMS and spin-diode effects, achieving 95% image classification accuracy in crossbar simulations.
-
An analog-electronic implementation of a harmonic oscillator recurrent neural network
An analog circuit implementing a four-node harmonic oscillator network preserves enough information to match its digital twin's sMNIST classification accuracy with a retrained linear readout.
-
Higher-Order Kuramoto Oscillator Network for Dense Associative Memory
A Kuramoto oscillator network with quartic Hebbian coupling stores patterns with superlinear capacity scaling and shows a tricritical point separating continuous from explosive retrieval.
-
Learning with springs and sticks
A damped spring-and-stick lattice performs regression by energy relaxation, and a reported 'thermodynamic learning barrier' sets the minimum free energy needed for learning.
-
Self-Organising Memristive Networks as Physical Learning Systems
Self-organising memristive networks exhibit collective nonlinear dynamics that can support physical learning with parallels to biological plasticity and potential for energy-efficient edge intelligence.
Discussion (0). Sign in to comment.