mlsanityData to 14 Oct 2026

Developmental Plasticity-inspired Adaptive Pruning for Deep Spiking and Artificial Neural Networks

arXiv 2211.12714 ↗First posted 23 Nov 2022cs.NE cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Developmental plasticity plays a prominent role in shaping the brain's structure during ongoing learning in response to dynamically changing environments. However, the existing network compression methods for deep artificial neural networks (ANNs) and spiking neural networks (SNNs) draw little inspiration from brain's developmental plasticity mechanisms, thus limiting their ability to learn efficiently, rapidly, and accurately. This paper proposed a developmental plasticity-inspired adaptive pruning (DPAP) method, with inspiration from the adaptive developmental pruning of dendritic spines, synapses, and neurons according to the ``use it or lose it, gradually decay" principle. The proposed DPAP model considers multiple biologically realistic mechanisms (such as dendritic spine dynamic plasticity, activity-dependent neural spiking trace, and local synaptic plasticity), with additional adaptive pruning strategy, so that the network structure can be dynamically optimized during learning without any pre-training and retraining. Extensive comparative experiments show consistent and remarkable performance and speed boost with the extremely compressed networks on a diverse set of benchmark tasks for deep ANNs and SNNs, especially the spatio-temporal joint pruning of SNNs in neuromorphic datasets. This work explores how developmental plasticity enables complex deep networks to gradually evolve into brain-like efficient and compact structures, eventually achieving state-of-the-art (SOTA) performance for biologically realistic SNNs.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 29 of its 99 references that are in the map. First posted on arXiv 23 Nov 2022.

Builds on

29 of 99 references.

References · 29

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  3. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  4. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  5. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 702
  6. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
  7. 2016Learning Structured Sparsity in Deep Neural Networkscited by 541
  8. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 442
  9. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
  10. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  11. 2018Soft Filter Pruning for Accelerating Deep Convolutional Neural Networkscited by 315
  12. 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 314
17 more
  1. 2019Sparse Networks from Scratch: Faster Training without Losing Performancecited by 213
  2. 2017Data-Driven Sparse Structure Selection for Deep Neural Networkscited by 181
  3. 2019Towards Optimal Structured CNN Pruning via Generative Adversarial Learningcited by 146
  4. 2019Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networkscited by 118
  5. 2015Data-free parameter pruning for Deep Neural Networkscited by 112
  6. 2020Channel Pruning via Automatic Structure Searchcited by 85
  7. 2019Pruning from Scratchcited by 72
  8. 2017STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognitioncited by 46
  9. 2019Comprehensive SNN Compression Using ADMM Optimization and Activity Regularizationcited by 45
  10. 2021Pruning of Deep Spiking Neural Networks through Gradient Rewiringcited by 43
  11. 2017An Entropy-based Pruning Method for CNN Compressioncited by 37
  12. 2022BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulationcited by 33
  13. 2021A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detectioncited by 31
  14. 2015Stochastic Synapses Enable Efficient Brain-Inspired Learning Machinescited by 21
  15. 2021Energy-efficient Knowledge Distillation for Spiking Neural Networkscited by 11
  16. 2020Connection Pruning for Deep Spiking Neural Networks with On-Chip Learningcited by 8
  17. 2018Efficient Hardware Realization of Convolutional Neural Networks using Intra-Kernel Regular Pruningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 2; 2026: 1.

6 papers.

  1. 2023Enhancing Efficient Continual Learning with Dynamic Structure Development of Spiking Neural Networkscited by 10
  2. 2024Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNNcited by 10
  3. 2025Continual Learning of Multiple Cognitive Functions with Brain-inspired Temporal Development Mechanismcited by 1
  4. 2025Efficient Training of Spiking Neural Networks by Spike-aware Data Pruningcited by 1
  5. 2024Topology Optimization of Random Memristors for Input-Aware Dynamic SNNcited by 0
  6. 2026Effective pruning of task-trained recurrent neural networks using noisy fluctuations and connection rescalingcited by 0