# Machine learning using magnetic stochastic synapses

arXiv: https://arxiv.org/abs/2303.01886 · HTML: https://mlsanity.com/paper/2303.01886/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 70 references that are in the map.
- First posted on arXiv 3 Mar 2023.

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

- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [MuProp: Unbiased Backpropagation for Stochastic Neural Networks](https://mlsanity.com/paper/1511.05176/) (2015)
- [Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines](https://mlsanity.com/paper/1511.04484/) (2015)
- [A unified view of likelihood ratio and reparameterization gradients](https://mlsanity.com/paper/2105.14900/) (2021)
- [A perspective on physical reservoir computing with nanomagnetic devices](https://mlsanity.com/paper/2212.04851/) (2022)
- [sBSNN: Stochastic-Bits Enabled Binary Spiking Neural Network with On-Chip Learning for Energy Efficient Neuromorphic Computing at the Edge](https://mlsanity.com/paper/2002.11163/) (2020)
- [In-Memory Resistive RAM Implementation of Binarized Neural Networks for Medical Applications](https://mlsanity.com/paper/2006.11595/) (2020)
- [Quantifying the Computational Capability of a Nanomagnetic Reservoir Computing Platform with Emergent Magnetization Dynamics](https://mlsanity.com/paper/2111.14603/) (2021)
- [Energy Efficient Learning with Low Resolution Stochastic Domain Wall Synapse Based Deep Neural Networks](https://mlsanity.com/paper/2111.07284/) (2021)
- [A generalised framework for detailed classification of swimming paths inside the Morris Water Maze](https://mlsanity.com/paper/1711.07446/) (2017)
- [Domain Wall Leaky Integrate-and-Fire Neurons with Shape-Based Configurable Activation Functions](https://mlsanity.com/paper/2011.06075/) (2020)

## Abstract (arXiv)

The impressive performance of artificial neural networks has come at the cost of high energy usage and CO2 emissions. Unconventional computing architectures, with magnetic systems as a candidate, have potential as alternative energy-efficient hardware, but, still face challenges, such as stochastic behaviour, in implementation. Here, we present a methodology for exploiting the traditionally detrimental stochastic effects in magnetic domain-wall motion in nanowires. We demonstrate functional binary stochastic synapses alongside a gradient learning rule that allows their training with applicability to a range of stochastic systems. The rule, utilising the mean and variance of the neuronal output distribution, finds a trade-off between synaptic stochasticity and energy efficiency depending on the number of measurements of each synapse. For single measurements, the rule results in binary synapses with minimal stochasticity, sacrificing potential performance for robustness. For multiple measurements, synaptic distributions are broad, approximating better-performing continuous synapses. This observation allows us to choose design principles depending on the desired performance and the device's operational speed and energy cost. We verify performance on physical hardware, showing it is comparable to a standard neural network.