Zhang et al., 2024 - Google Patents
A multi-granularity CNN pruning framework via deformable soft mask with joint trainingZhang et al., 2024
- Document ID
- 15673093403096050975
- Author
- Zhang P
- Tian C
- Zhao L
- Duan Z
- Publication year
- Publication venue
- Neurocomputing
External Links
Snippet
Abstract Model pruning is a commonly used technique for compressing DNNs and reducing computation requirements to accelerate inference. However, the required granularity of pruning varies across different application scenarios, making it difficult and cumbersome to …
- 238000013138 pruning 0 title abstract description 228
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | A multi-granularity CNN pruning framework via deformable soft mask with joint training | |
| Van Niekerk et al. | A new avenue for Bayesian inference with INLA | |
| CN110222820A (en) | Convolutional neural networks compression method based on weight beta pruning and quantization | |
| JP2017513127A5 (en) | ||
| Maass | On the computational power of winner-take-all | |
| Ernoult et al. | Updates of equilibrium prop match gradients of backprop through time in an RNN with static input | |
| CN113421237B (en) | No-reference image quality evaluation method based on depth feature transfer learning | |
| Mardani-Aghabaglou et al. | Assessment and prediction of cement paste flow behavior; Marsh-funnel flow time and mini-slump values | |
| Khademi et al. | The problem of demand effects in power studies: Moving beyond power priming | |
| CN109993302A (en) | Convolutional Neural Network Channel Self-selective Compression and Acceleration Method Based on Knowledge Transfer | |
| Golestaneh et al. | Fuzzy wavelet extreme learning machine | |
| WO2020087991A1 (en) | Hardware acceleration method for convolutional neural network inference and device therefor | |
| CN109063835B (en) | Compression device and method of neural network | |
| Zhao et al. | Feature selection of generalized extreme learning machine for regression problems | |
| CN110324613A (en) | A kind of deep learning image evaluation method towards video transmission quality | |
| Ceniceros | A semi-implicit moving mesh method for the focusing nonlinear Schrödinger equation | |
| DE69029538T2 (en) | Learning process, neural network and computer to simulate such a neural network | |
| Hu et al. | Research on model compression for embedded platform through quantization and pruning | |
| Bischoff | Applications of a mathematical model for drug distribution in mammals | |
| US20220050941A1 (en) | Method for solving complete flutter termination parameter based on double mass bodies of non-fixed constraint | |
| Barbieri et al. | Middle-class flight from post-Katrina New Orleans: A theoretical analysis of inequality and schooling | |
| CN110141237B (en) | A data-driven blind deconvolution method for fMRI images | |
| Ikuta et al. | Multi-layer perceptron with glial network for solving two-spiral problem | |
| Kulkarni et al. | Scalable digital CMOS architecture for spike based supervised learning | |
| Royce | Re-evaluation of isometric training methods and results, a must |