# BackEISNN: A Deep Spiking Neural Network with Adaptive Self-Feedback and Balanced Excitatory-Inhibitory Neurons

arXiv: https://arxiv.org/abs/2105.13004 · HTML: https://mlsanity.com/paper/2105.13004/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2021.

## Built on by (most cited first, 22 of 22)

- [Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networks](https://mlsanity.com/paper/2110.08858/) (2021)
- [Shrinking Your TimeStep: Towards Low-Latency Neuromorphic Object Recognition with Spiking Neural Network](https://mlsanity.com/paper/2401.01912/) (2024)
- [Spike Calibration: Fast and Accurate Conversion of Spiking Neural Network for Object Detection and Segmentation](https://mlsanity.com/paper/2207.02702/) (2022)
- [Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Future](https://mlsanity.com/paper/2304.06540/) (2023)
- [A Synapse-Threshold Synergistic Learning Approach for Spiking Neural Networks](https://mlsanity.com/paper/2206.06129/) (2022)
- [Self-Distillation Learning Based on Temporal-Spatial Consistency for Spiking Neural Networks](https://mlsanity.com/paper/2406.07862/) (2024)
- [Hadamard product in deep learning: Introduction, Advances and Challenges](https://mlsanity.com/paper/2504.13112/) (2025)
- [Spiking CapsNet: A Spiking Neural Network With A Biologically Plausible Routing Rule Between Capsules](https://mlsanity.com/paper/2111.07785/) (2021)
- [Astrocyte-Enabled Advancements in Spiking Neural Networks for Large Language Modeling](https://mlsanity.com/paper/2312.07625/) (2023)
- [Ultra-low Latency Spiking Neural Networks with Spatio-Temporal Compression and Synaptic Convolutional Block](https://mlsanity.com/paper/2203.10006/) (2022)
- [Exploiting High Performance Spiking Neural Networks with Efficient Spiking Patterns](https://mlsanity.com/paper/2301.12356/) (2023)
- [Multi-Bit Mechanism: A Novel Information Transmission Paradigm for Spiking Neural Networks](https://mlsanity.com/paper/2407.05739/) (2024)
- [Models Developed for Spiking Neural Networks](https://mlsanity.com/paper/2212.04377/) (2022)
- [Event USKT : U-State Space Model in Knowledge Transfer for Event Cameras](https://mlsanity.com/paper/2411.15276/) (2024)
- [AR-LIF: Adaptive reset leaky integrate-and-fire neuron for spiking neural networks](https://mlsanity.com/paper/2507.20746/) (2025)
- [Curriculum Design Helps Spiking Neural Networks to Classify Time Series](https://mlsanity.com/paper/2401.10257/) (2023)
- [Spike-TBR: a Noise Resilient Neuromorphic Event Representation](https://mlsanity.com/paper/2506.04817/) (2025)
- [Learning Spiking Neural Network from Easy to Hard task](https://mlsanity.com/paper/2309.04737/) (2023)
- [A Neural Architecture Search Method using Auxiliary Evaluation Metric based on ResNet Architecture](https://mlsanity.com/paper/2505.01313/) (2025)
- [STF: Shallow-Level Temporal Feedback to Enhance Spiking Transformers](https://mlsanity.com/paper/2508.00387/) (2025)
- [XOResNet: Exclusive-OR Meta-Residuals Facilitate Deep Spiking Neural Networks Learning](https://mlsanity.com/paper/2605.30362/) (2026)
- [Signed Spiking Neuron Enabled by an Orthogonal-Easy-Axis Magnetic Tunnel Junction](https://mlsanity.com/paper/2606.03796/) (2026)

## Abstract (arXiv)

Spiking neural networks (SNNs) transmit information through discrete spikes, which performs well in processing spatial-temporal information. Due to the non-differentiable characteristic, there still exist difficulties in designing well-performed SNNs. Recently, SNNs trained with backpropagation have shown superior performance due to the proposal of the gradient approximation. However, the performance on complex tasks is still far away from the deep neural networks. Taking inspiration from the autapse in the brain which connects the spiking neurons with a self-feedback connection, we apply an adaptive time-delayed self-feedback on the membrane potential to regulate the spike precisions. As well as, we apply the balanced excitatory and inhibitory neurons mechanism to control the spiking neurons' output dynamically. With the combination of the two mechanisms, we propose a deep spiking neural network with adaptive self-feedback and balanced excitatory and inhibitory neurons (BackEISNN). The experimental results on several standard datasets have shown that the two modules not only accelerate the convergence of the network but also improve the accuracy. For the MNIST, FashionMNIST, and N-MNIST datasets, our model has achieved state-of-the-art performance. For the CIFAR10 dataset, our BackEISNN also gets remarkable performance on a relatively light structure that competes against state-of-the-art SNNs.