# Bruno: Backpropagation Running Undersampled for Novel device Optimization

arXiv: https://arxiv.org/abs/2505.17791 · HTML: https://mlsanity.com/paper/2505.17791/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 23 May 2025.

## Builds on (most cited first, 17 of 17)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks](https://mlsanity.com/paper/1910.07407/) (2019)
- [Estimating or Propagating Gradients Through Stochastic Neurons](https://mlsanity.com/paper/1305.2982/) (2013)
- [PokeBNN: A Binary Pursuit of Lightweight Accuracy](https://mlsanity.com/paper/2112.00133/) (2021)
- [A flexible and fast PyTorch toolkit for simulating training and inference on analog crossbar arrays](https://mlsanity.com/paper/2104.02184/) (2021)
- [ReckOn: A 28nm Sub-mm2 Task-Agnostic Spiking Recurrent Neural Network Processor Enabling On-Chip Learning over Second-Long Timescales](https://mlsanity.com/paper/2208.09759/) (2022)
- [Online Spatio-Temporal Learning in Deep Neural Networks](https://mlsanity.com/paper/2007.12723/) (2020)
- [Algorithm for Training Neural Networks on Resistive Device Arrays](https://mlsanity.com/paper/1909.07908/) (2019)
- [ETLP: Event-based Three-factor Local Plasticity for online learning with neuromorphic hardware](https://mlsanity.com/paper/2301.08281/) (2023)
- [Online Spatio-Temporal Learning with Target Projection](https://mlsanity.com/paper/2304.05124/) (2023)
- [Braille Letter Reading: A Benchmark for Spatio-Temporal Pattern Recognition on Neuromorphic Hardware](https://mlsanity.com/paper/2205.15864/) (2022)
- [Online Training of Spiking Recurrent Neural Networks with Phase-Change Memory Synapses](https://mlsanity.com/paper/2108.01804/) (2021)
- [ST-MNIST -- The Spiking Tactile MNIST Neuromorphic Dataset](https://mlsanity.com/paper/2005.04319/) (2020)
- [Optimal Gradient Checkpointing for Sparse and Recurrent Architectures using Off-Chip Memory](https://mlsanity.com/paper/2412.11810/) (2024)
- [Low-Power Low-Latency Keyword Spotting and Adaptive Control with a SpiNNaker 2 Prototype and Comparison with Loihi](https://mlsanity.com/paper/2009.08921/) (2020)

## Abstract (arXiv)

Recent efforts to improve the efficiency of neuromorphic and machine learning systems have centred on developing of specialised hardware for neural networks. These systems typically feature architectures that go beyond the von Neumann model employed in general-purpose hardware such as GPUs, offering potential efficiency and performance gains. However, neural networks developed for specialised hardware must consider its specific characteristics. This requires novel training algorithms and accurate hardware models, since they cannot be abstracted as a general-purpose computing platform. In this work, we present a bottom-up approach to training neural networks for hardware-based spiking neurons and synapses, built using ferroelectric capacitors (FeCAPs) and resistive random-access memories (RRAMs), respectively. Unlike the common approach of designing hardware to fit abstract neuron or synapse models, we start with compact models of the physical device to model the computational primitives. Based on these models, we have developed a training algorithm (BRUNO) that can reliably train the networks, even when applying hardware limitations, such as stochasticity or low bit precision. We analyse and compare BRUNO with Backpropagation Through Time. We test it on different spatio-temporal datasets. First on a music prediction dataset, where a network composed of ferroelectric leaky integrate-and-fire (FeLIF) neurons is used to predict at each time step the next musical note that should be played. The second dataset consists on the classification of the Braille letters using a network composed of quantised RRAM synapses and FeLIF neurons. The performance of this network is then compared with that of networks composed of LIF neurons. Experimental results show the potential advantages of using BRUNO by reducing the time and memory required to detect spatio-temporal patterns with quantised synapses.