# Training Spiking Neural Networks with Local Tandem Learning

arXiv: https://arxiv.org/abs/2210.04532 · HTML: https://mlsanity.com/paper/2210.04532/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2022.

## Built on by (most cited first, 23 of 23)

- [Ternary Spike: Learning Ternary Spikes for Spiking Neural Networks](https://mlsanity.com/paper/2312.06372/) (2023)
- [Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks](https://mlsanity.com/paper/2302.14311/) (2023)
- [Direct Learning-Based Deep Spiking Neural Networks: A Review](https://mlsanity.com/paper/2305.19725/) (2023)
- [Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks](https://mlsanity.com/paper/2401.04486/) (2024)
- [Rethinking Spiking Neural Networks from an Ensemble Learning Perspective](https://mlsanity.com/paper/2502.14218/) (2025)
- [LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model](https://mlsanity.com/paper/2402.00411/) (2024)
- [FSTA-SNN:Frequency-based Spatial-Temporal Attention Module for Spiking Neural Networks](https://mlsanity.com/paper/2501.14744/) (2024)
- [Distance-Forward Learning: Enhancing the Forward-Forward Algorithm Towards High-Performance On-Chip Learning](https://mlsanity.com/paper/2408.14925/) (2024)
- [Deep Multi-Threshold Spiking-UNet for Image Processing](https://mlsanity.com/paper/2307.10974/) (2023)
- [Online Pseudo-Zeroth-Order Training of Neuromorphic Spiking Neural Networks](https://mlsanity.com/paper/2407.12516/) (2024)
- [Enhancing SNN-based Spatio-Temporal Learning: A Benchmark Dataset and Cross-Modality Attention Model](https://mlsanity.com/paper/2410.15689/) (2024)
- [ReverB-SNN: Reversing Bit of the Weight and Activation for Spiking Neural Networks](https://mlsanity.com/paper/2506.07720/) (2025)
- [Towards Chip-in-the-loop Spiking Neural Network Training via Metropolis-Hastings Sampling](https://mlsanity.com/paper/2402.06284/) (2024)
- [FAS: Fast ANN-SNN Conversion for Spiking Large Language Models](https://mlsanity.com/paper/2502.04405/) (2025)
- [Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers](https://mlsanity.com/paper/2510.07924/) (2025)
- [Deep Pulse-Coupled Neural Networks](https://mlsanity.com/paper/2401.08649/) (2023)
- [IML-Spikeformer: Input-aware Multi-Level Spiking Transformer for Speech Processing](https://mlsanity.com/paper/2507.07396/) (2025)
- [Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and Learnable Gradients](https://mlsanity.com/paper/2605.27412/) (2026)
- [Rethinking SNN Online Training and Deployment: Gradient-Coherent Learning via Hybrid-Driven LIF Model](https://mlsanity.com/paper/2410.07547/) (2024)
- [A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks](https://mlsanity.com/paper/2508.12609/) (2025)
- [Quantization Meets Spikes: Nearly Lossless Conversion at the First Timestep via Polarity Multi-Spike Mapping](https://mlsanity.com/paper/2508.14520/) (2025)
- [Batch Normalization-Free Fully Integer Quantized Neural Networks via Progressive Tandem Learning](https://mlsanity.com/paper/2512.16476/) (2025)
- [STARS: Spike Tail-Aware Relational Synthesis for ANN-to-SNN Data-Free Knowledge Distillation](https://mlsanity.com/paper/2605.27409/) (2026)

## Abstract (arXiv)

Spiking neural networks (SNNs) are shown to be more biologically plausible and energy efficient over their predecessors. However, there is a lack of an efficient and generalized training method for deep SNNs, especially for deployment on analog computing substrates. In this paper, we put forward a generalized learning rule, termed Local Tandem Learning (LTL). The LTL rule follows the teacher-student learning approach by mimicking the intermediate feature representations of a pre-trained ANN. By decoupling the learning of network layers and leveraging highly informative supervisor signals, we demonstrate rapid network convergence within five training epochs on the CIFAR-10 dataset while having low computational complexity. Our experimental results have also shown that the SNNs thus trained can achieve comparable accuracies to their teacher ANNs on CIFAR-10, CIFAR-100, and Tiny ImageNet datasets. Moreover, the proposed LTL rule is hardware friendly. It can be easily implemented on-chip to perform fast parameter calibration and provide robustness against the notorious device non-ideality issues. It, therefore, opens up a myriad of opportunities for training and deployment of SNN on ultra-low-power mixed-signal neuromorphic computing chips.10