Training deep physical neural networks with local physical information bottleneck

• URL: http://arxiv.org/abs/2602.09569v1
• Date: Tue, 10 Feb 2026 09:20:12 GMT
• Title: Training deep physical neural networks with local physical information bottleneck
• Authors: Hao Wang, Ziao Wang, Xiangpeng Liang, Han Zhao, Jianqi Hu, Junjie Jiang, Xing Fu, Jianshi Tang, Huaqiang Wu, Sylvain Gigan, Qiang Liu,
• Abstract summary: Deep learning has revolutionized modern society but faces growing energy and latency constraints.<n>We present the Physical Information Bottleneck (PIB), a framework that integrates information theory and local learning.<n>PIB adapts to severe hardware faults and allows for parallel training via geographically distributed resources.
• Score: 21.46485164162144
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning has revolutionized modern society but faces growing energy and latency constraints. Deep physical neural networks (PNNs) are interconnected computing systems that directly exploit analog dynamics for energy-efficient, ultrafast AI execution. Realizing this potential, however, requires universal training methods tailored to physical intricacies. Here, we present the Physical Information Bottleneck (PIB), a general and efficient framework that integrates information theory and local learning, enabling deep PNNs to learn under arbitrary physical dynamics. By allocating matrix-based information bottlenecks to each unit, we demonstrate supervised, unsupervised, and reinforcement learning across electronic memristive chips and optical computing platforms. PIB also adapts to severe hardware faults and allows for parallel training via geographically distributed resources. Bypassing auxiliary digital models and contrastive measurements, PIB recasts PNN training as an intrinsic, scalable information-theoretic process compatible with diverse physical substrates.

Related papers

• Self-Organising Memristive Networks as Physical Learning Systems [0.8752279866335758]
  Learning with physical systems is an emerging paradigm that seeks to harness the intrinsic nonlinear dynamics of physical substrates for learning.<n>This Perspective highlights one promising approach using physical networks comprised of resistive memory nanoscale components.<n>The overarching aim of this Perspective is to show how the convergence of nanotechnology, statistical physics, complex systems, and self-organising principles offers a unique opportunity to advance a new generation of physical intelligence technologies.
  arXiv  Detail & Related papers  (2025-08-31T08:44:02Z)
• Blending Optimal Control and Biologically Plausible Learning for Noise-Robust Physical Neural Networks [0.9423257767158634]
  Physical neural networks (PNNs) offer efficient neuromorphic information processing.<n>We propose a training approach for substantially reducing this training cost.<n>In addition to the reduction of training time, this approach achieves robust processing even under measurement errors and noise.
  arXiv  Detail & Related papers  (2025-02-26T11:10:40Z)
• Multistable Physical Neural Networks [1.3499500088995462]
  Physical Neural Networks (PNNs) offer the opportunity to view common materials and physical phenomena as networks. In this work, we incorporated mechanical bistability into PNNs, enabling memory and a direct link between computation and physical action. The insights gained from our study pave the way for the implementation of intelligent structures in smart tech, metamaterials, medical devices, soft robotics, and other fields.
  arXiv  Detail & Related papers  (2024-05-31T13:24:39Z)
• Mechanistic Neural Networks for Scientific Machine Learning [58.99592521721158]
  We present Mechanistic Neural Networks, a neural network design for machine learning applications in the sciences. It incorporates a new Mechanistic Block in standard architectures to explicitly learn governing differential equations as representations. Central to our approach is a novel Relaxed Linear Programming solver (NeuRLP) inspired by a technique that reduces solving linear ODEs to solving linear programs.
  arXiv  Detail & Related papers  (2024-02-20T15:23:24Z)
• ETLP: Event-based Three-factor Local Plasticity for online learning with neuromorphic hardware [105.54048699217668]
  We show a competitive performance in accuracy with a clear advantage in the computational complexity for Event-Based Three-factor Local Plasticity (ETLP) We also show that when using local plasticity, threshold adaptation in spiking neurons and a recurrent topology are necessary to learntemporal patterns with a rich temporal structure.
  arXiv  Detail & Related papers  (2023-01-19T19:45:42Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Physical Deep Learning with Biologically Plausible Training Method [2.5608506499175094]
  We present physical deep learning by extending a biologically plausible training algorithm called direct feedback alignment. We can emulate and accelerate the computation for this training on a simple and scalable physical system. Our results provide practical solutions for the training and acceleration of neuromorphic computation.
  arXiv  Detail & Related papers  (2022-04-01T05:46:16Z)
• Physics-informed ConvNet: Learning Physical Field from a Shallow Neural Network [0.180476943513092]
  Modelling and forecasting multi-physical systems remain a challenge due to unavoidable data scarcity and noise. New framework named physics-informed convolutional network (PICN) is recommended from a CNN perspective. PICN may become an alternative neural network solver in physics-informed machine learning.
  arXiv  Detail & Related papers  (2022-01-26T14:35:58Z)
• Credit Assignment in Neural Networks through Deep Feedback Control [59.14935871979047]
  Deep Feedback Control (DFC) is a new learning method that uses a feedback controller to drive a deep neural network to match a desired output target and whose control signal can be used for credit assignment. The resulting learning rule is fully local in space and time and approximates Gauss-Newton optimization for a wide range of connectivity patterns. To further underline its biological plausibility, we relate DFC to a multi-compartment model of cortical pyramidal neurons with a local voltage-dependent synaptic plasticity rule, consistent with recent theories of dendritic processing.
  arXiv  Detail & Related papers  (2021-06-15T05:30:17Z)
• Learning Contact Dynamics using Physically Structured Neural Networks [81.73947303886753]
  We use connections between deep neural networks and differential equations to design a family of deep network architectures for representing contact dynamics between objects. We show that these networks can learn discontinuous contact events in a data-efficient manner from noisy observations. Our results indicate that an idealised form of touch feedback is a key component of making this learning problem tractable.
  arXiv  Detail & Related papers  (2021-02-22T17:33:51Z)
• Deep Learning for Ultra-Reliable and Low-Latency Communications in 6G Networks [84.2155885234293]
  We first summarize how to apply data-driven supervised deep learning and deep reinforcement learning in URLLC. To address these open problems, we develop a multi-level architecture that enables device intelligence, edge intelligence, and cloud intelligence for URLLC.
  arXiv  Detail & Related papers  (2020-02-22T14:38:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.