AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

LTMD: Learning Improvement of Spiking Neural Networks with Learnable Thresholding Neurons and Moderate Dropout

Siqi Wang, Tee Hiang Cheng, Meng-Hiot Lim

NeurIPS 2022 · Architectures and efficiency › Spiking networks · approach: Sparse efficient spiking sequence models · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add learnable thresholding to LIF neurons (ablation)SNN · MNIST (4 timesteps)accuracy (%): 99.53 -> 99.57Improved
add moderate dropout on top of learnable thresholding (ablation)SNN with LT · MNIST (4 timesteps)accuracy (%): 99.57 -> 99.60Improved
add learnable thresholding to LIF neurons (ablation)SNN · CIFAR10 (2 timesteps)accuracy (%): 92.88 -> 93.51Improved
add moderate dropout on top of learnable thresholding (ablation)SNN with LT · CIFAR10 (2 timesteps)accuracy (%): 93.51 -> 93.75Improved
add learnable thresholding to LIF neurons (ablation)SNN · N-MNIST (15 timesteps)accuracy (%): 99.55 -> 99.58Improved
add moderate dropout on top of learnable thresholding (ablation)SNN with LT · N-MNIST (15 timesteps)accuracy (%): 99.58 -> 99.65Improved
add learnable thresholding to LIF neurons (ablation)SNN · DVS-CIFAR10 (7 timesteps)accuracy (%): 71.30 -> 72.30Improved
vary initial threshold k (0.5 vs 0) (ablation)SNN with learnable thresholding · CIFAR10, DVS-CIFAR10accuracyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy