A Case-based Reasoning with Feature Weights Derived by BP Network

Peng, Yan; Zhuang, Like

doi:10.1109/iita.2007.98

Cited by 6 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Weber et al [64] claim a philosophic overlap with the Korean work in an ANN-CBR hybrid; yet the details of the feature-weighting used are not clear. Peng and Zhuang [65] propose a different feature-weighting scheme for an ANN-CBR twinning, that replaces feature-values of a case using the MLPs weights (but does not reference the Korean work). However, it is only in the last few years, that the Korean work has been seriously revisited.…”

Section: Korean Developments (1999-2007): Feature-weighting Tests Of ...mentioning

confidence: 99%

How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems

Keane

Kenny

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper proposes a theoretical analysis of one approach to the eXplainable AI (XAI) problem, using post-hoc explanation-by-example, that relies on the twinning of artificial neural networks (ANNs) with case-based reasoning (CBR) systems; so-called ANN-CBR twins. It surveys these systems to advance a new theoretical interpretation of previous work and define a road map for CBR's further role in XAI. A systematic survey of 1102 papers was conducted to identify a fragmented literature on this topic and trace its influence to more recent work involving deep neural networks (DNNs). The twin-system approach is advanced as one possible coherent, generic solution to the XAI problem. The paper concludes by road-mapping future directions for this XAI solution, considering (i) further tests of feature-weighting techniques, (ii) how explanatory cases might be deployed (e.g., in counterfactuals, a fortori cases), and (iii) the unwelcome, much-ignored issue of user evaluation.

show abstract

Section: Korean Developments (1999-2007): Feature-weighting Tests Of ...mentioning

confidence: 99%

How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems

Keane

Kenny

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…According to the principle of CBR (case based reasoning) [8], ship maintenance cost case can be denoted by S=(U,Cu{d},j,V) , where U={ xPx2 , .. ,x n } is a source case base; C is the input attributes set denoting the feature of Xi and C = {cPc2, .. ·,cm} ; d is the decision attribute, i.e., the average maintenance cost corresponding to the input attributes; V is the value domain of input attributes and decision attribute,…”

Section: A Combined Fuzzy Clustering Algorithmmentioning

confidence: 99%

Research on similarity measure among ship maintenance cost cases based on a combined fuzzy clustering algorithm

Ru-xiang

2010

2010 International Conference on Future Information Technology and Management Engineering

View full text Add to dashboard Cite

Similarity measure among ship maintenance cost cases plays an important role in cost forecasting. A combined fuzzy clustering algorithm which integrates fuzzy transitive closure method and fuzzy c-means method is proposed to deal with this problem. In order to improve the performance of the combined algorithm, a weighted cosine distance method is also put forward to establish a more reasonable fuzzy similar matrix.The experiments show that the proposed fuzzy clustering algorithm can greatly improve the quality of case retrieval. The application of the combined algorithm is feasible and effective.

show abstract

“…The main concept of CBR is to solve new problems by adapting the successful solution of the similar past cases. It is widely applied in many domains [2][16] [21] [22]. In a CBR framework, the case representation is to describe a case by some features.…”

Section: Introductionmentioning

confidence: 99%

Case-Based Reasoning with feature clustering

Hong

Liou²

2008

2008 7th IEEE International Conference on Cognitive Informatics

View full text Add to dashboard Cite

Case-Based Reasoning (CBR) is the process of solving new problems based on the solutions of the similar past problems. Selecting important features to perform case retrieving can improve the efficiency of the large-scale CBR. In this paper, we select features based on attribute clustering. The representative attributes found in the clusters are thus used for indexing and representing cases such that retrieving similar cases based on representative attributes can reduce the execution time. In addition, the clustered attributes also make the CBR framework more flexible than other feature selection methods.Keywords-case-based reasoning, attribute clustering, feature space, similarity measure. I.Proc. 7th IEEE Int. Conf. on Cognitive Informatics (ICCI'08)

show abstract

A Case-based Reasoning with Feature Weights Derived by BP Network

Cited by 6 publications

References 2 publications

How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems

How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems

Research on similarity measure among ship maintenance cost cases based on a combined fuzzy clustering algorithm

Case-Based Reasoning with feature clustering

Contact Info

Product

Resources

About