# Noise-Aware Training of Neuromorphic Dynamic Device Networks

arXiv: https://arxiv.org/abs/2401.07387 · HTML: https://mlsanity.com/paper/2401.07387/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 57 references that are in the map.
- First posted on arXiv 14 Jan 2024.

## Builds on (most cited first, 16 of 16)

- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Scalable Gradients for Stochastic Differential Equations](https://mlsanity.com/paper/2001.01328/) (2020)
- [On Neural Differential Equations](https://mlsanity.com/paper/2202.02435/) (2022)
- [The Forward-Forward Algorithm: Some Preliminary Investigations](https://mlsanity.com/paper/2212.13345/) (2022)
- [Direct Feedback Alignment Provides Learning in Deep Neural Networks](https://mlsanity.com/paper/1609.01596/) (2016)
- [Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limit](https://mlsanity.com/paper/1905.09883/) (2019)
- [Neural SDEs as Infinite-Dimensional GANs](https://mlsanity.com/paper/2102.03657/) (2021)
- [Neural Jump Stochastic Differential Equations](https://mlsanity.com/paper/1905.10403/) (2019)
- [Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems](https://mlsanity.com/paper/2104.13386/) (2021)
- [Backpropagation-free Training of Deep Physical Neural Networks](https://mlsanity.com/paper/2304.11042/) (2023)
- [Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets](https://mlsanity.com/paper/1901.09049/) (2019)
- [Forecasting the outcome of spintronic experiments with Neural Ordinary Differential Equations](https://mlsanity.com/paper/2108.02318/) (2021)
- [GPTPU: Accelerating Applications using Edge Tensor Processing Units](https://mlsanity.com/paper/2107.05473/) (2021)
- [Quantifying the Computational Capability of a Nanomagnetic Reservoir Computing Platform with Emergent Magnetization Dynamics](https://mlsanity.com/paper/2111.14603/) (2021)

## Built on by (most cited first, 5 of 5)

- [Learning Nonlinear Heterogeneity in Physical Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2601.15340/) (2026)
- [The role of neuromorphic principles in the future of biomedicine and healthcare](https://mlsanity.com/paper/2603.27716/) (2026)
- [Intrinsic-Noise Consolidation: A Doob-Barrier-Conditioned Diffusion Turns Analog Device Noise into a Continual-Learning Resource](https://mlsanity.com/paper/2607.06924/) (2026)
- [In Dialogue with Intelligence: Rethinking Large Language Models as Collective Knowledge](https://mlsanity.com/paper/2505.22767/) (2025)
- [Low-power analogue neural networks with trainable nonlinear connections for continuous control](https://mlsanity.com/paper/2606.23742/) (2026)

## Abstract (arXiv)

Physical computing has the potential to enable widespread embodied intelligence by leveraging the intrinsic dynamics of complex systems for efficient sensing, processing, and interaction. While individual devices provide basic data processing capabilities, networks of interconnected devices can perform more complex and varied tasks. However, designing networks to perform dynamic tasks is challenging without physical models and accurate quantification of device noise. We propose a novel, noise-aware methodology for training device networks using Neural Stochastic Differential Equations (Neural-SDEs) as differentiable digital twins, accurately capturing the dynamics and associated stochasticity of devices with intrinsic memory. Our approach employs backpropagation through time and cascade learning, allowing networks to effectively exploit the temporal properties of physical devices. We validate our method on diverse networks of spintronic devices across temporal classification and regression benchmarks. By decoupling the training of individual device models from network training, our method reduces the required training data and provides a robust framework for programming dynamical devices without relying on analytical descriptions of their dynamics.