# Noise-based Local Learning using Stochastic Magnetic Tunnel Junctions

arXiv: https://arxiv.org/abs/2412.12783 · HTML: https://mlsanity.com/paper/2412.12783/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 42 references that are in the map.
- First posted on arXiv 17 Dec 2024.

## Builds on (most cited first, 11 of 11)

- [Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation](https://mlsanity.com/paper/1602.05179/) (2016)
- [Gradients without Backpropagation](https://mlsanity.com/paper/2202.08587/) (2022)
- [Scaling Forward Gradient With Local Losses](https://mlsanity.com/paper/2210.03310/) (2022)
- [Training End-to-End Analog Neural Networks with Equilibrium Propagation](https://mlsanity.com/paper/2006.01981/) (2020)
- [Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations](https://mlsanity.com/paper/2209.00530/) (2022)
- [Backpropagation-free Training of Deep Physical Neural Networks](https://mlsanity.com/paper/2304.11042/) (2023)
- [Self-learning Machines based on Hamiltonian Echo Backpropagation](https://mlsanity.com/paper/2103.04992/) (2021)
- [Learning by non-interfering feedback chemical signaling in physical networks](https://mlsanity.com/paper/2203.12098/) (2022)
- [Optimization without Backpropagation](https://mlsanity.com/paper/2209.06302/) (2022)
- [Constrained Parameter Inference as a Principle for Learning](https://mlsanity.com/paper/2203.13203/) (2022)
- [Gradient-Free Training of Recurrent Neural Networks using Random Perturbations](https://mlsanity.com/paper/2405.08967/) (2024)

## Built on by (most cited first, 2 of 2)

- [Neuromorphic Intelligence](https://mlsanity.com/paper/2509.11940/) (2025)
- [A Unified Perspective on Optimization in Machine Learning and Neuroscience: From Gradient Descent to Neural Adaptation](https://mlsanity.com/paper/2510.18812/) (2025)

## Abstract (arXiv)

Brain-inspired learning in physical hardware has enormous potential to learn fast at minimal energy expenditure. One of the characteristics of biological learning systems is their ability to learn in the presence of various noise sources. Inspired by this observation, we introduce a novel noise-based learning approach for physical systems implementing multi-layer neural networks. Simulation results show that our approach allows for effective learning whose performance approaches that of the conventional effective yet energy-costly backpropagation algorithm. Using a spintronics hardware implementation, we demonstrate experimentally that learning can be achieved in a small network composed of physical stochastic magnetic tunnel junctions. These results provide a path towards efficient learning in general physical systems which embraces rather than mitigates the noise inherent in physical devices.