Abstract
Modern neural networks are heavily over-parameterized. This redundancy incurs substantial compute and memory overhead during training and inference. Existing pruning methods rely on post-hoc magnitude thresholds or static initialization heuristics. Consequently, they often require manual per-layer sparsity targets or expensive retraining cycles. We propose Dynamic Activity-Dependent Pruning (DADP), a biologically inspired structural plasticity mechanism. During training, DADP measures connection importance via the accumulated product of pre-synaptic activations and post-synaptic error gradients. Using a single global threshold instead of fixed layer budgets, DADP dynamically allocates sparsity across network depth while naturally inducing neuron- and channel-level pruning. Across MLP, VGG-16, ResNet-18, BiLSTM-CRF, and MiniBERT architectures, DADP matches or outperforms Magnitude, SNIP and RigL, retaining 73.67% accuracy (dense baseline: 76.06%) at 99% sparsity on ResNet-18. Finally, matrix-based Shannon entropy and effective rank measurements confirm that DADP preserves latent feature diversity at extreme sparsities without representation collapse.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Deshpande, B. (2026). DADP: Dynamic Activity-Dependent Pruning, A Reverse Hebbian-Inspired Structural Pruning Method. https://omanscience.com/en/articles/dadp-dynamic-activity-dependent-pruning-a-reverse-hebbian-inspired-structural-pruning-method
MLA 9
Deshpande, Bhushan. "DADP: Dynamic Activity-Dependent Pruning, A Reverse Hebbian-Inspired Structural Pruning Method." https://omanscience.com/en/articles/dadp-dynamic-activity-dependent-pruning-a-reverse-hebbian-inspired-structural-pruning-method.
Chicago (author–date)
Deshpande, Bhushan. 2026. "DADP: Dynamic Activity-Dependent Pruning, A Reverse Hebbian-Inspired Structural Pruning Method." https://omanscience.com/en/articles/dadp-dynamic-activity-dependent-pruning-a-reverse-hebbian-inspired-structural-pruning-method.
Harvard
Deshpande, B. (2026) 'DADP: Dynamic Activity-Dependent Pruning, A Reverse Hebbian-Inspired Structural Pruning Method', Available at: https://omanscience.com/en/articles/dadp-dynamic-activity-dependent-pruning-a-reverse-hebbian-inspired-structural-pruning-method.
Vancouver
Deshpande B. DADP: Dynamic Activity-Dependent Pruning, A Reverse Hebbian-Inspired Structural Pruning Method. https://omanscience.com/en/articles/dadp-dynamic-activity-dependent-pruning-a-reverse-hebbian-inspired-structural-pruning-method
IEEE
B. Deshpande, "DADP: Dynamic Activity-Dependent Pruning, A Reverse Hebbian-Inspired Structural Pruning Method," https://omanscience.com/en/articles/dadp-dynamic-activity-dependent-pruning-a-reverse-hebbian-inspired-structural-pruning-method.