.png){kind=icon}
返回
XMAP: eXplainable mapping analytical process
.png){kind=icon}
OA
AI
DOI：10.1007/s40747-021-00583-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As the number of artificial intelligence (AI) applications increases rapidly and more people will be affected by AI's decisions, there are real needs for novel AI systems that can deliver both accuracy and explanations. To address these needs, this paper proposes a new approach called eXplainable Mapping Analytical Process (XMAP). Different from existing works in explainable AI, XMAP is highly modularised and the interpretability for each step can be easily obtained and visualised. A number of core algorithms are developed in XMAP to capture the distributions and topological structures of data, define contexts that emerged from data, and build effective representations for classification tasks. The experiments show that XMAP can provide useful and interpretable insights across analytical steps. For the binary classification task, its predictive performance is very competitive as compared to advanced machine learning algorithms in the literature. In some large datasets, XMAP can even outperform black-box algorithms without losing its interpretability.
Keyword:
Explainable artificial intelligence
Context-aware machine learning
Classification
期刊
IF:
4.6
论文数:
2.1K
被引数:
6.6K
机构
引用论文
分享收藏Fast interpolation-based t-SNE for improved visualization of single-cell RNA-seq data基于快速插值的t-sne可改善单细胞rna-seq数据的可视化.png)
NATURE METHODS
OAAI
NATURE METHODSIF32.1
OAAI分享收藏分享收藏Stability of Iodine in Iodized Salt Used for Correction of Iodine-Deficiency Disorders. II用于纠正碘缺乏病的碘盐中碘的稳定性。二
PREAI
分享收藏Interneuronal signalling is involved in induction of collateral sprouting of nociceptive axonsNeuroscience
NeuroscienceIF0
PREAI
分享收藏
查看更多内容