Visualisation and knowledge discovery from interpretable models

被引:3
作者
Ghosh, Sreejita [1 ]
Tino, Peter [2 ]
Bunte, Kerstin [1 ]
机构
[1] Univ Groningen, Bernoulli Inst, Groningen, Netherlands
[2] Univ Birmingham, Sch Comp Sci, Birmingham, W Midlands, England
来源
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) | 2020年
关键词
adaptive distances; learning vector quantization; non-linear visualization; explainable AI; SYSTEM;
D O I
10.1109/ijcnn48605.2020.9206702
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Increasing number of sectors which affect human lives, are using Machine Learning (ML) tools. Hence the need for understanding their working mechanism and evaluating their fairness in decision-making, are becoming paramount, ushering in the era of Explainable AI (XAI). In this contribution we introduced a few intrinsically interpretable models which are also capable of dealing with missing values, in addition to extracting knowledge from the dataset and about the problem. These models are also capable of visualisation of the classifier and decision boundaries: they are the angle based variants of Learning Vector Quantization. We have demonstrated the algorithms on a synthetic dataset and a real-world one (heart disease dataset from the UCI repository). The newly developed classifiers helped in investigating the complexities of the UCI dataset as a multiclass problem. The performance of the developed classifiers were comparable to those reported in literature for this dataset, with additional value of interpretability, when the dataset was treated as a binary class problem.
引用
收藏
页数:8
相关论文
共 23 条
  • [1] [Anonymous], 2007, J PHARM SOC WIS JAN
  • [2] Classification in high-dimensional spectral data: Accuracy vs. interpretability vs. model size
    Backhaus, Andreas
    Seiffert, Udo
    [J]. NEUROCOMPUTING, 2014, 131 : 15 - 22
  • [3] Benard, 2019, ARXIV190806852
  • [4] BREIMAN L, 2001, MACH LEARN, V45, P5, DOI DOI 10.1023/A:1010933404324
  • [5] Bunte K, 2016, NEW CHALLENGES NEURA, P20
  • [6] Limited Rank Matrix Learning, discriminative dimension reduction and visualization
    Bunte, Kerstin
    Schneider, Petra
    Hammer, Barbara
    Schleif, Frank-Michael
    Villmann, Thomas
    Biehl, Michael
    [J]. NEURAL NETWORKS, 2012, 26 : 159 - 173
  • [7] Adaptive local dissimilarity measures for discriminative dimension reduction of labeled data
    Bunte, Kerstin
    Hammer, Barbara
    Wismueller, Axel
    Biehl, Michael
    [J]. NEUROCOMPUTING, 2010, 73 (7-9) : 1074 - 1092
  • [8] Machine Learning Interpretability: A Survey on Methods and Metrics
    Carvalho, Diogo, V
    Pereira, Eduardo M.
    Cardoso, Jaime S.
    [J]. ELECTRONICS, 2019, 8 (08)
  • [9] SMOTE: Synthetic minority over-sampling technique
    Chawla, Nitesh V.
    Bowyer, Kevin W.
    Hall, Lawrence O.
    Kegelmeyer, W. Philip
    [J]. 2002, American Association for Artificial Intelligence (16)
  • [10] Doshi-Velez Finale., 2017, arXiv: Machine Learning