WEKO3
アイテム
Lifelong learning of human actions with deep neural network self-organization
https://oist.repo.nii.ac.jp/records/350
https://oist.repo.nii.ac.jp/records/350c4b3738b-cc79-4456-aab2-2cc6edca26ee
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
1-s2.0-S0893608017302034-main (1.1 MB)
|
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
(https://creativecommons.org/licenses/by-nc-nd/4.0/) |
| Item type | 学術雑誌論文 / Journal Article(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2018-04-06 | |||||
| タイトル | ||||||
| タイトル | Lifelong learning of human actions with deep neural network self-organization | |||||
| 言語 | en | |||||
| 言語 | ||||||
| 言語 | eng | |||||
| 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 | |||||
| 著者（英） |
Parisi, German I.
× Parisi, German I.× Tani, Jun× Weber, Cornelius× Wermter, Stefan |
|||||
| 書誌情報 |
en : Neural Networks 巻 96, p. 137-149, 発行日 2017-09-20 |
|||||
| 抄録 | ||||||
| 内容記述タイプ | Other | |||||
| 内容記述 | Lifelong learning is fundamental in autonomous robotics for the acquisition and fine-tuning of knowledge through experience. However, conventional deep neural models for action recognition from videos do not account for lifelong learning but rather learn a batch of training data with a predefined number of action classes and samples. Thus, there is the need to develop learning systems with the ability to incrementally process available perceptual cues and to adapt their responses over time. We propose a self-organizing neural architecture for incrementally learning to classify human actions from video sequences. The architecture comprises growing self-organizing networks equipped with recurrent neurons for processing time-varying patterns. We use a set of hierarchically arranged recurrent networks for the unsupervised learning of action representations with increasingly large spatiotemporal receptive fields. Lifelong learning is achieved in terms of prediction-driven neural dynamics in which the growth and the adaptation of the recurrent networks are driven by their capability to reconstruct temporally ordered input sequences. Experimental results on a classification task using two action benchmark datasets show that our model is competitive with state-of-the-art methods for batch learning also when a significant number of sample labels are missing or corrupted during training sessions. Additional experiments show the ability of our model to adapt to non-stationary input avoiding catastrophic interference. | |||||
| 出版者 | ||||||
| 出版者 | Elsevier | |||||
| ISSN | ||||||
| 収録物識別子タイプ | ISSN | |||||
| 収録物識別子 | 0893-6080 | |||||
| PubMed番号 | ||||||
| 関連タイプ | isIdenticalTo | |||||
| 識別子タイプ | PMID | |||||
| 関連識別子 | info:pmid/29017140 | |||||
| DOI | ||||||
| 関連タイプ | isIdenticalTo | |||||
| 識別子タイプ | DOI | |||||
| 関連識別子 | info:doi/10.1016/j.neunet.2017.09.001 | |||||
| 権利 | ||||||
| 権利情報 | © 2017 The Authors | |||||
| 関連サイト | ||||||
| 識別子タイプ | URI | |||||
| 関連識別子 | http://www.sciencedirect.com/science/article/pii/S0893608017302034 | |||||
| 著者版フラグ | ||||||
| 出版タイプ | VoR | |||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
