[ICLR 2023] "More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity"; [ICML 2023] "Are Large Kernels Better Teachers than Transformers for ConvNets?"
-
Updated
Jul 5, 2023 - HTML
[ICLR 2023] "More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity"; [ICML 2023] "Are Large Kernels Better Teachers than Transformers for ConvNets?"
[NeurIPS'21] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang
Event-driven Computation for Brain Dynamics.
This project implements a self-pruning neural network for CIFAR-10 classification, where learnable gate parameters enable dynamic removal of less important weights during training. Using L1 regularization, the model achieves sparsity while maintaining competitive accuracy, improving efficiency.
To associate your repository with the dynamic-sparsity topic, visit your repo's landing page and select "manage topics."