Polynomial dendritic neural networks
文献类型：期刊论文
| 作者 | Chen, Yuwen1,2 ; Liu, Jiang1
|
| 刊名 | NEURAL COMPUTING & APPLICATIONS
 |
| 出版日期 | 2022-02-22 |
| 页码 | 18 |
| 关键词 | Dendritic action Interpretability Polynomial neural networks White-box model |
| ISSN号 | 0941-0643 |
| DOI | 10.1007/s00521-022-07044-4 |
| 通讯作者 | Liu, Jiang(liujiang@cigit.ac.cn) |
| 英文摘要 | Although many artificial neural networks have achieved success in practical applications, there is still a concern among many over their "black box" nature. Why and how do they work? Recently, some interesting interpretations have been made through polynomial regression as an alternative to neural networks. Polynomial networks have thus received more and more attention as generators of polynomial regression. Furthermore, some special polynomial works, such as dendrite net (DD) and Kileel et al.'s deep polynomial neural networks, showed that some single neurons have powerful computability. This agrees with a recent discovery on biological neurons, that is, a single biological neuron can perform XOR operations. Inspired by such works, we propose a new model called the polynomial dendritic neural network (PDN) in this article. The PDN achieves powerful computability on a single neuron in a neural network. The output of a PDN is a high degree polynomial of the inputs. To obtain its parameter values, we took PDN as a neural network and employed the back-propagation method. As shown in this context, PDN contains more polynomial outputs than DD and deep polynomial neural networks. We deliberately studied two special PDNs called the exponential PDN (EPDN) and asymptotic PDN (APDN). For interpretability, we proposed a feature analysis method based on the coefficients of the polynomial outputs of such PDNs. The EPDN and APDN showed satisfactory accuracy, precision, recall, F1 score, and AUC in several experiments. Furthermore, we found the coefficient-based interpretability to be effective on some actual health cases. |
| 资助项目 | National Key R&D Program of China[2018YFC0116704] ; NSF of China[61672488] ; Science and Technology Service Network Initiative[KFJ-STS-QYZD-2021-01-001] ; Youth Innovation Promotion Association of Chinese Academy of Sciences[2020377] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000759356100002 |
| 出版者 | SPRINGER LONDON LTD |
| 源URL | [http://119.78.100.138/handle/2HOD01W0/15384]  |
| 专题 | 中国科学院重庆绿色智能技术研究院 |
| 通讯作者 | Liu, Jiang |
| 作者单位 | 1.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing, Peoples R China 2.Chinese Acad Sci, Chengdu Inst Comp Applicat, Chengdu, Peoples R China |
| 推荐引用方式 GB/T 7714 | Chen, Yuwen,Liu, Jiang. Polynomial dendritic neural networks[J]. NEURAL COMPUTING & APPLICATIONS,2022:18. |
| APA | Chen, Yuwen,&Liu, Jiang.(2022).Polynomial dendritic neural networks.NEURAL COMPUTING & APPLICATIONS,18. |
| MLA | Chen, Yuwen,et al."Polynomial dendritic neural networks".NEURAL COMPUTING & APPLICATIONS (2022):18. |
入库方式： OAI收割
来源：重庆绿色智能技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。