WEKO3
アイテム
Evaluating Learning Potential with Internal States in Deep Neural Networks
http://hdl.handle.net/10228/0002000737
http://hdl.handle.net/10228/00020007373d23ba14-e2d1-462a-8de1-d20357288b5e
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
neuro_50.pdf (707 KB)
|
|
| アイテムタイプ | 学術雑誌論文 = Journal Article(1) | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2024-06-06 | |||||||||||||
| 資源タイプ | ||||||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||||||
| 資源タイプ | journal article | |||||||||||||
| タイトル | ||||||||||||||
| タイトル | Evaluating Learning Potential with Internal States in Deep Neural Networks | |||||||||||||
| 言語 | en | |||||||||||||
| 言語 | ||||||||||||||
| 言語 | eng | |||||||||||||
| 著者 |
Takasaki, Shogo
× Takasaki, Shogo
× 榎田, 修一
WEKO
32516
|
|||||||||||||
| 抄録 | ||||||||||||||
| 内容記述タイプ | Abstract | |||||||||||||
| 内容記述 | Deploying deep learning models on small-scale computing devices necessitates considering computational resources. However, reducing the model size to accommodate these resources often results in a trade-off with accuracy. The iterative process of training and validating to optimize model size and accuracy can be inefficient. A potential solution to this dilemma is the extrapolation of learning curves, which evaluates a model’s potential based on initial learning curves. As a result, it is possible to efficiently search for a network that achieves a balance between accuracy and model size. Nonetheless, we posit that a more effective approach to analyzing the latent potential of training models is to focus on the internal state, rather than merely relying on the validation scores. In this vein, we propose a module dedicated to scrutinizing the network’s internal state, with the goal of automating the optimization of both accuracy and network size. Specifically, this paper delves into analyzing the latent potential of the network by leveraging the internal state of the Long Short-Term Memory (LSTM) in a traffic accident prediction network. | |||||||||||||
| 言語 | en | |||||||||||||
| 備考 | ||||||||||||||
| 内容記述タイプ | Other | |||||||||||||
| 内容記述 | 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, February 27-29, 2024, Rome, Italy | |||||||||||||
| 言語 | en | |||||||||||||
| 書誌情報 |
en : Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2 VISAPP: VISAPP p. 317-324, 発行日 2024 |
|||||||||||||
| 出版社 | ||||||||||||||
| 出版者 | ScitePress | |||||||||||||
| 言語 | en | |||||||||||||
| DOI | ||||||||||||||
| 識別子タイプ | DOI | |||||||||||||
| 関連識別子 | https://doi.org/10.5220/0012298500003660 | |||||||||||||
| ISSN | ||||||||||||||
| 収録物識別子タイプ | EISSN | |||||||||||||
| 収録物識別子 | 2184-4321 | |||||||||||||
| 著作権関連情報 | ||||||||||||||
| 権利情報 | Copyright (c) 2024 by SCITEPRESS – Science and Technology Publications, Lda. Paper published under CC license (CC BY-NC-ND 4.0) | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Deep Learning | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Anticipating Accidents | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Long Short-Term Memory | |||||||||||||
| キーワード | ||||||||||||||
| 主題Scheme | Other | |||||||||||||
| 主題 | Evaluating Learning Potential | |||||||||||||
| 出版タイプ | ||||||||||||||
| 出版タイプ | VoR | |||||||||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||||||
| 査読の有無 | ||||||||||||||
| 値 | yes | |||||||||||||
