A Case-Based Explanation System for Black-Box Systems

Most users of machine-learning products are reluctant to use them without any sense of the underlying logic that has led to the system’s predictions. Unfortunately many of these systems lack any transparency in the way they operate and are deemed to be black boxes. In this paper we present a Case-Based Reasoning (CBR) solution to providing supporting explanations of black-box systems. This CBR solution has two key facets; it uses local information to assess the importance of each feature and using this, it selects the cases from the data used to build the black-box system for use in explanation. The retrieval mechanism takes advantage of the derived feature importance information to help select cases that are a better reflection of the black-box solution and thus more convincing explanations.

[1]  Agnar Aamodt,et al.  Explanation in Case-Based Reasoning–Perspectives and Goals , 2005, Artificial Intelligence Review.

[2]  Joachim Diederich,et al.  Survey and critique of techniques for extracting rules from trained artificial neural networks , 1995, Knowl. Based Syst..

[3]  Andrew W. Moore,et al.  Locally Weighted Learning , 1997, Artificial Intelligence Review.

[4]  Jörg Cassens,et al.  Explanation Goals in Case-Based Reasoning , 2004 .

[5]  D. Gentner,et al.  Learning and Transfer: A General Role for Analogical Encoding , 2003 .

[6]  J. Cassens.  Knowing What to Explain and When , 2004 .

[7]  Padraig Cunningham,et al.  An Evaluation of the Usefulness of Case-Based Explanation , 2003, ICCBR.

[8]  Pedro M. Domingos.  Knowledge Discovery Via Multiple Models , 1998, Intell. Data Anal..

[9]  Padraig Cunningham,et al.  Explanation Oriented Retrieval , 2004, ECCBR.

[10]  Padraig Cunningham,et al.  An artificial neural network ensemble to predict disposition and length of stay in children presenting with bronchiolitis , 2004, European journal of emergency medicine : official journal of the European Society for Emergency Medicine.

[11]  Zhi-Hua Zhou,et al.  Medical diagnosis with C4.5 rule preceded by artificial neural network ensemble , 2003, IEEE Transactions on Information Technology in Biomedicine.

[12]  Les Gasser,et al.  On using artificial intelligence to integrate the design of organizational and process change in US manufacturing , 2005, AI & SOCIETY.

[13]  David McSherry,et al.  Explaining the Pros and Cons of Conclusions in CBR , 2004, ECCBR.

[14]  Joachim Diederich,et al.  The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks , 1998, IEEE Trans. Neural Networks.