Pith. sign in

REVIEW 5 cited by

CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.04663 v5 pith:VZMAFJXM submitted 2024-02-07 cs.NE

Yulong Huang , Xiaopeng Lin , Hongwei Ren , Haotian Fu , Yue Zhou , Zunchang Liu , Biao Pan , Bojun Cheng This is my paper · ORCID
classification cs.NE
keywords clifsnnsannsintegrate-and-fireleakynetworksneuralneuron
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Compared to conventional deep Artificial Neural Networks (ANNs), SNNs exhibit superior efficiency and capability to process temporal information. However, it remains a challenge to train SNNs due to their undifferentiable spiking mechanism. The surrogate gradients method is commonly used to train SNNs, but often comes with an accuracy disadvantage over ANNs counterpart. We link the degraded accuracy to the vanishing of gradient on the temporal dimension through the analytical and experimental study of the training process of Leaky Integrate-and-Fire (LIF) Neuron-based SNNs. Moreover, we propose the Complementary Leaky Integrate-and-Fire (CLIF) Neuron. CLIF creates extra paths to facilitate the backpropagation in computing temporal gradient while keeping binary output. CLIF is hyperparameter-free and features broad applicability. Extensive experiments on a variety of datasets demonstrate CLIF's clear performance advantage over other neuron models. Furthermore, the CLIF's performance even slightly surpasses superior ANNs with identical network structure and training conditions. The code is available at https://github.com/HuuYuLong/Complementary-LIF.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning

    cs.NE 2025-06 conditional novelty 6.0 of 10

    SPEAR combines a linear-regression SynOps estimator with a target-aware reward to search structured pruning policies for spiking neural networks under a SynOps budget.

  2. Improving Performance of Spike-based Deep Q-Learning using Ternary Neurons

    cs.LG 2025-06 conditional novelty 6.0 of 10

    An asymmetric ternary spiking neuron with a trainable negative threshold improves deep spiking Q-network scores on six of seven Atari games, but the theoretical explanation and the headline performance metric are not ...

  3. SDSNN: A Single-Timestep Spiking Neural Network with Self-Dropping Neuron and Bayesian Optimization

    cs.NE 2025-08 reject novelty 5.0 of 10

    A network using decay-triggered Self-Dropping neurons and Bayesian per-layer time-step search reports Fashion-MNIST 93.72%, CIFAR-10 92.20%, and CIFAR-100 69.45% accuracy with 21-56% energy savings versus multi-timestep LIF.

  4. Optimization of Low-Latency Spiking Neural Networks Utilizing Historical Dynamics of Refractory Periods

    cs.NE 2025-06 conditional novelty 5.0 of 10

    A refractory period that adapts using the neuron's membrane potential derivative and its own history improves low-latency spiking network accuracy, cuts redundant spikes, and boosts noise robustness.

  5. Integrating Complexity and Biological Realism: High-Performance Spiking Neural Networks for Breast Cancer Detection

    cs.NE 2025-06 reject novelty 4.0 of 10

    Spiking neural networks combined with Lempel-Ziv complexity reach up to 98.25% accuracy on the Wisconsin breast cancer dataset, but the result lacks error bars, code, and a working threshold rule for the Levy-Baxter neuron.

Pith tools