# Supervised training of spiking neural networks for robust deployment on mixed-signal neuromorphic processors

arXiv: https://arxiv.org/abs/2102.06408 · HTML: https://mlsanity.com/paper/2102.06408/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 65 references that are in the map.
- First posted on arXiv 12 Feb 2021.

## Builds on (most cited first, 21 of 21)

- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Training Deep Spiking Neural Networks using Backpropagation](https://mlsanity.com/paper/1608.08782/) (2016)
- [A Simple Way to Initialize Recurrent Networks of Rectified Linear Units](https://mlsanity.com/paper/1504.00941/) (2015)
- [Weight Agnostic Neural Networks](https://mlsanity.com/paper/1906.04358/) (2019)
- [Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rules](https://mlsanity.com/paper/1801.05219/) (2018)
- [Event-Based Backpropagation can compute Exact Gradients for Spiking Neural Networks](https://mlsanity.com/paper/2009.08378/) (2020)
- [A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)](https://mlsanity.com/paper/1708.04198/) (2017)
- [Neuromorphic Deep Learning Machines](https://mlsanity.com/paper/1612.05596/) (2016)
- [A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends](https://mlsanity.com/paper/1905.13294/) (2019)
- [Efficient keyword spotting using dilated convolutions and gating](https://mlsanity.com/paper/1811.07684/) (2018)
- [Demonstrating Advantages of Neuromorphic Computation: A Pilot Study](https://mlsanity.com/paper/1811.03618/) (2018)
- [Supervised Learning in Spiking Neural Networks with FORCE Training](https://mlsanity.com/paper/1609.02545/) (2016)
- [Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network](https://mlsanity.com/paper/1702.06463/) (2017)
- [The brain as an efficient and robust adaptive learner](https://mlsanity.com/paper/1705.08031/) (2017)
- [The importance of space and time in neuromorphic cognitive agents](https://mlsanity.com/paper/1902.09791/) (2019)
- [Learning to represent signals spike by spike](https://mlsanity.com/paper/1703.03777/) (2017)
- [An Accelerated LIF Neuronal Network Array for a Large Scale Mixed-Signal Neuromorphic Architecture](https://mlsanity.com/paper/1804.01906/) (2018)
- [Neuromorphic Learning towards Nano Second Precision](https://mlsanity.com/paper/1309.4283/) (2013)
- [Implementing efficient balanced networks with mixed-signal spike-based learning circuits](https://mlsanity.com/paper/2010.14353/) (2020)

## Built on by (most cited first, 7 of 7)

- [Network insensitivity to parameter noise via adversarial regularization](https://mlsanity.com/paper/2106.05009/) (2021)
- [Closed-form control with spike coding networks](https://mlsanity.com/paper/2212.12887/) (2022)
- [Gradient-descent hardware-aware training and deployment for mixed-signal Neuromorphic processors](https://mlsanity.com/paper/2303.12167/) (2023)
- [Distributed Representations Enable Robust Multi-Timescale Symbolic Computation in Neuromorphic Hardware](https://mlsanity.com/paper/2405.01305/) (2024)
- [Spatiotemporal Pattern Recognition in Single Mixed-Signal VLSI Neurons with Heterogeneous Dynamic Synapses](https://mlsanity.com/paper/2106.05686/) (2021)
- [Membrane Potential Distribution Adjustment and Parametric Surrogate Gradient in Spiking Neural Networks](https://mlsanity.com/paper/2304.13289/) (2023)
- [Practical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape Smoothing](https://mlsanity.com/paper/2604.08624/) (2026)

## Abstract (arXiv)

Mixed-signal analog/digital circuits emulate spiking neurons and synapses with extremely high energy efficiency, an approach known as "neuromorphic engineering". However, analog circuits are sensitive to process-induced variation among transistors in a chip ("device mismatch"). For neuromorphic implementation of Spiking Neural Networks (SNNs), mismatch causes parameter variation between identically-configured neurons and synapses. Each chip exhibits a different distribution of neural parameters, causing deployed networks to respond differently between chips. Current solutions to mitigate mismatch based on per-chip calibration or on-chip learning entail increased design complexity, area and cost, making deployment of neuromorphic devices expensive and difficult. Here we present a supervised learning approach that produces SNNs with high robustness to mismatch and other common sources of noise. Our method trains SNNs to perform temporal classification tasks by mimicking a pre-trained dynamical system, using a local learning rule from non-linear control theory. We demonstrate our method on two tasks requiring memory, and measure the robustness of our approach to several forms of noise and mismatch. We show that our approach is more robust than common alternatives for training SNNs. Our method provides robust deployment of pre-trained networks on mixed-signal neuromorphic hardware, without requiring per-device training or calibration.