.png){kind=icon}
返回
Extracting reduced logic programs from artificial neural networks
.png){kind=icon}
OA
AI
DOI：10.1007/s10489-008-0142-y.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Artificial neural networks can be trained to perform excellently in many application areas. Whilst they can learn from raw data to solve sophisticated recognition and analysis problems, the acquired knowledge remains hidden within the network architecture and is not readily accessible for analysis or further use: Trained networks are black boxes. Recent research efforts therefore investigate the possibility to extract symbolic knowledge from trained networks, in order to analyze, validate, and reuse the structural insights gained implicitly during the training process. In this paper, we will study how knowledge in form of propositional logic programs can be obtained in such a way that the programs are as simple as possible-where simple is being understood in some clearly defined and meaningful way.
Keyword:
Artificial neural network
Rule extraction
Logic program
Neural-symbolic integration
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Approximating the semantics of logic programs by recurrent neural networks.png)
APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏分享收藏
New metabolic activity of the nonsulfated sulfakinin Zopat-SK-1 in the insect fat bodyPeptides
PeptidesIF0
PREAI
分享收藏
查看更多内容