Symbolic Interpretation of Artificial Neural Networks

By Ismail Abdel Hamid Taha, Joydeep Ghosh. 1999

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “Multi-Layer Neural Networks Explanation by simplification Rule-based learner: [82, 83, 147, 148, 246, 247, 248, 249, 250, 251]”
Explaining Explanations: An Overview of Interpretability of Machine Learning (2018, background): “Some of these sampling approaches only work on binary input [34] or use genetic algorithms to produce new training examples [35].”
Rule Extraction Algorithm for Deep Neural Networks: A Review (2016, background): “Taha and Ghosh [25] have proposed three rule extraction algorithms.”
A multiple kernel support vector machine scheme for feature selection and rule extraction from gene expression data of cancer tissue (2007, methodology): “The approaches of rule extraction from ANN can be categorized as: link rule extraction techniques, black-box rule extraction techniques, extracting fuzzy rules and extracting rules from recurrent networks [40].”
Rule Extraction from Support Vector Machines: An Overview of Issues and Application in Credit Scoring (2008, methodology): “CART (1984) [11] P C + R Decision tree induction CN2 (1989) [15] P C Rule induction C4.5 (1993) [49] P C Decision tree induction TREPAN (1996) [18] P C Decision tree induction, M-of-N splits BIO-RE (1999) [ 56 ] P C Creates complete truth table, only applicable to toy problems”
Explaining Explanations: An Approach to Evaluating Interpretability of Machine Learning (2018, background): “Some of these sampling approaches only work on binary input [34] or use genetic algorithms to produce new training examples [35].”
Binary Rule Generation via Hamming Clustering (2002, methodology): “The former includes all the techniques [5], [6] that”
Understanding the Crucial Role of Attribute Interaction in Data Mining (2001, background): “However, despite the progress in the area of extracting comprehensible rules from neural nets (see Taha and Ghosh (1999), Vaughn (1996)) this extraction still remains a difficult, cumbersome task.”
Extracting rules from multilayer perceptrons in classification problems: A clustering-based approach (2006, methodology): “Taha and Gosh developed three rule extraction algorithms [64,65] and also a methodology to evaluate the extracted rules [66].”
Model-Agnostic Linear Competitors - When Interpretable Models Compete and Collaborate with Black-Box Models (2019, result): “…body of continuous work on neural-symbolic or neural-expert systems (Garcez et al. 2015) pursued by a relatively small research community over the last two decades and has yielded several signiﬁcant results (McGarry et al. 1999, Garcez et al. 2012, Taha and Ghosh 1999, Towell and Shavlik 1994).”
Rule Extraction from Neural Network by Genetic Algorithm with Pareto Optimization (2004, background): “The fidelity of GenPar is about 96 %, what is comparable with the results of other methods (for example 97 % for FullRe [6]), but it offers the user the easy way to decide which objective is the most important one.”
Credit rating analysis with support vector machines and neural networks: a market comparative study (2004, methodology): “Other researchers used the connection strengths to extract symbolic rules [40] in order to provide interpretation capability similar to that of decision tree algorithms.”