請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/101347完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 施吉昇 | zh_TW |
| dc.contributor.advisor | Chi-Sheng Shih | en |
| dc.contributor.author | 曾貴鴻 | zh_TW |
| dc.contributor.author | Kuei-Hung Tseng | en |
| dc.date.accessioned | 2026-01-27T16:04:58Z | - |
| dc.date.available | 2026-01-28 | - |
| dc.date.copyright | 2026-01-27 | - |
| dc.date.issued | 2026 | - |
| dc.date.submitted | 2026-01-21 | - |
| dc.identifier.citation | [1] H. Li, C. Li, M. Xue, G. Fang, S. Zhou, Z. Feng, H. Wang, Y. Wang, L. Cheng, M. Song et al., “Pruningbench: A comprehensive benchmark of structural pruning,” arXiv preprint arXiv:2406.12315, 2024.
[2] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, and N. Houlsby, “An image is worth 16x16 words: Transformers for image recognition at scale,” in International Conference on Learning Representations, 2021. [Online]. Available: https://openreview.net/forum?id=YicbFdNTTy [3] OpenAI, J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, and e. a. Shyamal Anadkat, “Gpt-4 technical report,” 2024. [Online]. Available: https://arxiv.org/abs/2303.08774 [4] H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozière, N. Goyal, E. Hambro, F. Azhar, A. Rodriguez, A. Joulin, E. Grave, and G. Lample, “Llama: Open and efficient foundation language models,” 2023. [Online]. Available: https://arxiv.org/abs/2302.13971 [5] DeepSeek-AI, A. Liu, B. Feng, B. Xue, B. Wang, B. Wu, C. Lu, and e. a. Chenggang Zhao, “Deepseek-v3 technical report,” 2025. [Online]. Available: https://arxiv.org/abs/2412.19437 [6] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. [7] H. Touvron, M. Cord, M. Douze, F. Massa, A. Sablayrolles, and H. Jegou, “Training data-efficient image transformers and distillation through attention,” in International Conference on Machine Learning, vol. 139, July 2021, pp. 10 347–10 357. [8] G. Xiao, J. Lin, M. Seznec, H. Wu, J. Demouth, and S. Han, “SmoothQuant: Accurate and efficient post-training quantization for large language models,” in Proceedings of the 40th International Conference on Machine Learning, 2023. [9] J. Lin, J. Tang, H. Tang, S. Yang, W.-M. Chen, W.-C. Wang, G. Xiao, X. Dang, C. Gan, and S. Han, “Awq: Activation-aware weight quantization for llm compression and acceleration,” in MLSys, 2024. [10] S. Han, H. Mao, and W. J. Dally, “Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding,” in 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings, Y. Bengio and Y. LeCun, Eds., 2016. [Online]. Available: http://arxiv.org/abs/1510.00149 [11] A. Mishra, J. A. Latorre, J. Pool, D. Stosic, D. Stosic, G. Venkatesh, C. Yu, and P. Micikevicius, “Accelerating sparse deep neural networks,” 2021. [Online]. Available: https://arxiv.org/abs/2104.08378 [12] G. Fang, X. Ma, M. Song, M. Bi Mi, and X. Wang, “Depgraph: Towards any structural pruning,” in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 16 091–16 101. [13] Z. Liu, M. Sun, T. Zhou, G. Huang, and T. Darrell, “Rethinking the value of network pruning,” in International Conference on Learning Representations, 2019. [Online]. Available: https://openreview.net/forum?id=rJlnB3C5Ym [14] S. Han, J. Pool, J. Tran, and W. Dally, “Learning both weights and connections for efficient neural network,” in Advances in Neural Information Processing Systems, C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett, Eds., vol. 28. Curran Associates, Inc., 2015. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2015/file/ae0eb3eed39d2bcef4622b2499a05fe6-Paper.pdf [15] H. Wang, C. Qin, Y. Zhang, and Y. Fu, “Neural pruning via growing regularization,” in International Conference on Learning Representations, 2021. [16] A. Chavan, Z. Shen, Z. Liu, Z. Liu, K.-T. Cheng, and E. Xing, “Vision transformer slimming: Multi-dimension searching in continuous optimization space,” in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 4921–4931. [17] H. Li, A. Kadav, I. Durdanovic, H. Samet, and H. P. Graf, “Pruning filters for efficient convnets,” in International Conference on Learning Representations, 2017. [18] J. Lee, S. Park, S. Mo, S. Ahn, and J. Shin, “Layer-adaptive sparsity for the magnitude-based pruning,” in International Conference on Learning Representations, 2021. [Online]. Available: https://openreview.net/forum?id=H6ATjJ0TKdf [19] Y. LeCun, J. Denker, and S. Solla, “Optimal brain damage,” in Advances in Neural Information Processing Systems, D. Touretzky, Ed., vol. 2. Morgan-Kaufmann, 1989 [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/1989/file/6c9882bbac1c7093bd25041881277658-Paper.pdf [20] P. Molchanov, A. Mallya, S. Tyree, I. Frosio, and J. Kautz, “Importance estimation for neural network pruning,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 11 256–11 264. [21] Y. He, P. Liu, Z. Wang, Z. Hu, and Y. Yang, “Filter pruning via geometric median for deep convolutional neural networks acceleration,” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 4335–4344. [22] A. Jacot, F. Gabriel, and C. Hongler, “Neural tangent kernel: Convergence and generalization in neural networks,” in Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett, Eds., vol. 31. Curran Associates, Inc., 2018. [23] E. Frantar and D. Alistarh, “Optimal brain compression: A framework for accurate post-training quantization and pruning,” in Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh, Eds., vol. 35. Curran Associates, Inc., 2022, pp. 4475–4488. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2022/file/1caf09c9f4e6b0150b06a07e77f2710c-Paper-Conference.pdf [24] G. Ling, Z. Wang, YuliangYan, and Q. Liu, “Slimgpt: Layer-wise structured pruning for large language models,” in The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024. [Online]. Available: https://openreview.net/forum?id=MxF0IKJtKW [25] B. Hassibi, D. Stork, and G. Wolff, “Optimal brain surgeon and general network pruning,” in IEEE International Conference on Neural Networks, 1993, pp. 293–299 vol.1. [26] C. Wang, R. Grosse, S. Fidler, and G. Zhang, “Eigendamage: Structured pruning in the kronecker-factored eigenbasis,” in Proceedings of the 36th International Conference on Machine Learning (ICML 2019), 2019. [27] R. Yu, A. Li, C.-F. Chen, J.-H. Lai, V. I. Morariu, X. Han, M. Gao, C.-Y. Lin, and L. S. Davis, “Nisp: Pruning networks using neuron importance score propagation,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp.9194–9203. [28] J.-H. Luo, J. Wu, and W. Lin, “Thinet: A filter level pruning method for deep neural network compression,” in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 5068–5076. [29] L. Iurada, M. Ciccone, and T. Tommasi, “Finding lottery tickets in vision models via data-driven spectral foresight pruning,” in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 16 142–16 151. [30] D. Mittal, S. Bhardwaj, M. M. Khapra, and B. Ravindran, “Recovering from random pruning: On the plasticity of deep convolutional neural networks,” in 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 2018, pp. 848–857. [31] Y. He, X. Zhang, and J. Sun, “Channel pruning for accelerating very deep neural networks,” in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1398–1406. [32] Z. Liu, J. Li, Z. Shen, G. Huang, S. Yan, and C. Zhang, “Learning efficient convolutional networks through network slimming,” in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2755–2763. [33] L. Yu and W. Xiang, “X-pruner: explainable pruning for vision transformers,” in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp.24 355–24 363. [34] F. Ilhan, G. Su, S. F. Tekin, T. Huang, S. Hu, and L. Liu, “Resource- efficient transformer pruning for finetuning of large models,” in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 16 206–16 215. [35] Y. Rao, W. Zhao, B. Liu, J. Lu, J. Zhou, and C.-J. Hsieh, “Dynamicvit: efficient vision transformers with dynamic token sparsification,” in Proceedings of the 35th International Conference on Neural Information Processing Systems, ser. NIPS ’21. Red Hook, NY, USA: Curran Associates Inc., 2024. [36] H. Wang, B. Dedhia, and N. K. Jha, “Zero-tprune: Zero-shot token pruning through leveraging of the attention graph in pre-trained transformers,” in 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, pp. 16 070–16 079. [37] D. Bolya, C.-Y. Fu, X. Dai, P. Zhang, C. Feichtenhofer, and J. Hoffman, “Token merging: Your ViT but faster,” in International Conference on Learning Representations, 2023. [38] J. Lee, L. Xiao, S. S. Schoenholz, Y. Bahri, R. Novak, J. Sohl-Dickstein, and J. Pennington, Wide neural networks of any depth evolve as linear models under gradient descent. Red Hook, NY, USA: Curran Associates Inc., 2019. [39] B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y. Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” in Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, ser. Proceedings of Machine Learning Research, A. Singh and J. Zhu, Eds., vol. 54. PMLR, 20–22 Apr 2017, pp. 1273–1282. [Online]. Available: https://proceedings.mlr.press/v54/mcmahan17a.html [40] D. Bolya, C.-Y. Fu, X. Dai, P. Zhang, C. Feichtenhofer, and J. Hoffman, “Token merging: Your vit but faster,” in The Eleventh International Conference on Learning Representations, 2023. [Online]. Available: https://openreview.net/forum?id=JroZRaRw7Eu [41] M. Kim, S. Gao, Y.-C. Hsu, Y. Shen, and H. Jin, “Token fusion: Bridging the gap between token pruning and token merging,” in 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, pp. 1372–1381. [42] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel,P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [43] A. Krizhevsky, “Learning multiple layers of features from tiny images,” University of Toronto, 05 2012. [44] G. V. Horn, macaodha, Maggie, and W. Kan, “inaturalist 2019 at fgvc6,” https:// kaggle.com/competitions/inaturalist-2019-fgvc6, 2019, kaggle. [45] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei, “ImageNet Large Scale Visual Recognition Challenge,” International Journal of Computer Vision (IJCV), vol. 115, no. 3, pp. 211–252, 2015. [46] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “Imagenet: A largescale hierarchical image database,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 248–255. [47] C. Sun, A. Shrivastava, S. Singh, and A. Gupta, “Revisiting unreasonable effectiveness of data in deep learning era,” in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 843–852. [48] I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” in International Conference on Learning Representations, 2019. [Online]. Available: https://openreview.net/forum?id=Bkg6RiCqY7 [49] E. J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, and W. Chen, “LoRA: Low-rank adaptation of large language models,” in International Conference on Learning Representations, 2022. [Online]. Available: https://openreview.net/forum?id=nZeVKeeFYf9 [50] R. Varghese and S. M., “Yolov8: A novel object detection algorithm with enhanced performance and robustness,” in 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), 2024, pp. 1–6. [51] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei, “Imagenet large scale visual recognition challenge,” International Journal of Computer Vision (IJCV), vol. 115, no. 3, pp. 211–252, 2015. [52] S. Merity, C. Xiong, J. Bradbury, and R. Socher, “Pointer sentinel mixture models,” 2016. [53] M. P. Marcus, B. Santorini, and M. A. Marcinkiewicz, “Building a large annotated corpus of English: The Penn Treebank,” Computational Linguistics, vol. 19, no. 2, pp. 313–330, 1993. [Online]. Available: https://aclanthology.org/J93-2004/ [54] Y. Bisk, R. Zellers, R. L. Bras, J. Gao, and Y. Choi, “Piqa: Reasoning about physical commonsense in natural language,” in Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020. [55] K. Sakaguchi, R. L. Bras, C. Bhagavatula, and Y. Choi, “Winogrande: an adversarial winograd schema challenge at scale,” Commun. ACM, vol. 64, no. 9, pp. 99–106, Aug. 2021. [Online]. Available: https://doi.org/10.1145/3474381 [56] R. Zellers, A. Holtzman, Y. Bisk, A. Farhadi, and Y. Choi, “Hellaswag: Can a machine really finish your sentence?” in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019. [57] P. Clark, I. Cowhey, O. Etzioni, T. Khot, A. Sabharwal, C. Schoenick, and O. Tafjord, “Think you have solved question answering? try arc, the ai2 reasoning challenge,” arXiv:1803.05457v1, 2018. [58] T. Mihaylov, P. Clark, T. Khot, and A. Sabharwal, “Can a suit of armor conduct electricity? a new dataset for open book question answering,” in EMNLP, 2018. [59] C. Christopher, L. Kenton, C. Ming-Wei, K. Tom, C. Michael, and T. Kristina, “Boolq: Exploring the surprising difficulty of natural yes/no questions,” in NAACL, 2019. [60] R. Taori, I. Gulrajani, T. Zhang, Y. Dubois, X. Li, C. Guestrin, P. Liang, and T. B. Hashimoto, “Stanford alpaca: An instruction-following llama model,” https: //github.com/tatsu-lab/stanford_alpaca, 2023. [61] S. Gao, C.-H. Lin, T. Hua, T. Zheng, Y. Shen, H. Jin, and Y.-C. Hsu, “Disp-llm: Dimension-independent structural pruning for large language models,” in Advances in Neural Information Processing Systems, A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang, Eds., vol. 37. Curran Associates, Inc., 2024, pp. 72 219–72 244. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2024/file/84a7fc24ed52e8eff514c33e8ac76ea3-Paper-Conference.pdf | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/101347 | - |
| dc.description.abstract | 深度神經網路在各種應用中展現了優異的成果，但其對空間與運算資源的需求，對於資源受限的設備構成了重大的挑戰。模型剪枝（model pruning）透過移除較不重要的權重來解決此問題，通常會再進行微調（fine-tuning）以恢復性能。儘管已有研究顯示，在剪枝後更新權重可以提升結果，但這些方法往往依賴特定的剪枝準則，限制了其通用性。本研究提出了一種名為 WeightCompression 的有效且具彈性的方式，在微調前，將被剪除的權重重新分配到各層中保留的權重上。這樣的重分配機制為微調提供了更佳的初始化，使得本方法僅需一次剪枝步驟，即可達到與傳統多次剪枝方法相當的效能。與現有方法相比，WeightCompression 可將剪枝流程加速 3.27 倍至 12.58 倍，同時維持競爭力的準確率。此外，該方法對剪枝準則具有高度的適應性，並可有效擴展至大型模型。實驗結果顯示，WeightCompression 是一個靈活且高效的剪枝後權重更新方法。 | zh_TW |
| dc.description.abstract | Deep neural networks have shown promising results across a wide range of applications, but the requirements on space and computation present significant challenges for deployment on resource-constrained devices. Model pruning addresses this issue by removing less important weights, typically followed by fine-tuning to recover the performance. While prior work has shown that updating weights after pruning can improve results, these approaches are often tied to specific pruning criteria, limiting their generality. This work proposes WeightCompression, an effective and flexible method that redistributes pruned weights into the remaining ones within each layer before fine-tuning. This redistribution provides a better initialization for fine-tuning, enabling the proposed method to match the performance of iterative pruning approaches using only a single pruning step. Compared to existing methods, WeightCompression accelerates the pruning process by 3.27x to 12.58x while maintaining competitive accuracy. Last but not the least, it is agnostic to the choice of pruning criterion and scales well to large models. The results suggest that WeightCompression can be a flexible and efficient framework for post-pruning weight updates. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2026-01-27T16:04:58Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2026-01-27T16:04:58Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員審定書i
誌謝iii 摘要v Abstract vii Contents ix List of Figures xiii List of Tables xv Chapter 1 Introduction 1 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.3 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . 4 Chapter 2 Background and Related Works 7 2.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.1.1 Pruning Criteria . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.1.2 Pruning Scenarios . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.1.3 Pruning Tools . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 2.2 Neural Tangent Kernel . . . . . . . . . . . . . . . . . . . . . . . . . 12 2.3 Related Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 2.3.1 Optimal Brain Damage and Optimal Brain Surgery . . . . . . . . . 14 2.3.2 Optimal Brain Compression and SlimGPT . . . . . . . . . . . . . . 15 Chapter 3 System Architecture and Problem Definition 17 3.1 Assumptions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 3.2 Problem Formulation . . . . . . . . . . . . . . . . . . . . . . . . . . 19 3.3 Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 Chapter 4 Methodology 23 4.1 Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 4.1.1 Concept of WeightCompression . . . . . . . . . . . . . . . . . . . 23 4.1.2 WeightCompression and Pruning Pipeline . . . . . . . . . . . . . . 24 4.2 Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26 Chapter 5 Experiments 29 5.1 Experimental Setup . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 5.1.1 Evaluation Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . 30 5.1.2 Evaluation Model . . . . . . . . . . . . . . . . . . . . . . . . . . . 31 5.1.3 Training Configuration . . . . . . . . . . . . . . . . . . . . . . . . 32 5.1.4 Evaluation Procedure . . . . . . . . . . . . . . . . . . . . . . . . . 33 5.2 One-shot and Iterative Pruning Results . . . . . . . . . . . . . . . . 35 5.3 Comparison of SlimGPT and WeightCompression under One-shot Pruning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 5.4 Fine-tuning Dynamics of One-shot and Iterative Pruning . . . . . . . 39 5.4.1 One-shot Pruning. . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 5.4.2 Iterative Pruning . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43 5.5 Ablation Study: Effect of Training Data Size . . . . . . . . . . . . . 47 5.6 Ablation Study: Importance of Weight Update Strategy Design . . . . 50 Chapter 6 Conclusion 53 6.1 Summary of Key Findings . . . . . . . . . . . . . . . . . . . . . . . 53 6.2 Limitations and Future Work . . . . . . . . . . . . . . . . . . . . . . 54 References 57 Appendix A — Convolutional Neural Network Experiments 65 A.1 Experiment Settings . . . . . . . . . . . . . . . . . . . . . . . . . . 65 A.2 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 66 Appendix B — Large Language Model Experiments 69 B.1 Experiment Settings . . . . . . . . . . . . . . . . . . . . . . . . . . 69 B.2 Result on LLaMA . . . . . . . . . . . . . . . . . . . . . . . . . . . 70 B.3 Ablation Study on LLaMA . . . . . . . . . . . . . . . . . . . . . . . 72 | - |
| dc.language.iso | en | - |
| dc.subject | 結構化剪枝 | - |
| dc.subject | 權重壓縮 | - |
| dc.subject | 權重重新分配 | - |
| dc.subject | 單次剪枝 | - |
| dc.subject | 微調 | - |
| dc.subject | 有效的模型壓縮 | - |
| dc.subject | Structural Pruning | - |
| dc.subject | Weight Compression | - |
| dc.subject | Weight Redistribution | - |
| dc.subject | One-shot Pruning | - |
| dc.subject | Fine-tuning | - |
| dc.subject | Efficient Model Compression | - |
| dc.title | 在結構剪枝中保留模型權重的方法 | zh_TW |
| dc.title | Structural Pruning without Losing Model Weights | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 114-1 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 林澤;洪士灝;郭峻因 | zh_TW |
| dc.contributor.oralexamcommittee | Che Lin;Shih-Hao Hung;Jiun-In Guo | en |
| dc.subject.keyword | 結構化剪枝,權重壓縮權重重新分配單次剪枝微調有效的模型壓縮 | zh_TW |
| dc.subject.keyword | Structural Pruning,Weight CompressionWeight RedistributionOne-shot PruningFine-tuningEfficient Model Compression | en |
| dc.relation.page | 73 | - |
| dc.identifier.doi | 10.6342/NTU202600167 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2026-01-22 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊工程學系 | - |
| dc.date.embargo-lift | 2028-01-20 | - |
| 顯示於系所單位： | 資訊工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-114-1.pdf 未授權公開取用 | 13.9 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。