Rule extraction from neural networks via decision tree induction

Sato, Masahiro; Tsukimoto, Hiroshi

doi:10.1109/ijcnn.2001.938448

Cited by 85 publications

(69 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A neural network encodes the SARs present in the dataset within the weights and biases that define the connections. A number of efforts have been made to interpret these weights and biases [14,37,75,90,98,99], though it was only recently that neural network QSAR models were considered. One approach to interpreting neural networks is based on linearizing the network [46] and is shown schematically in Fig.…”

Section: Interpretation Methodologiesmentioning

confidence: 99%

On the interpretation and interpretability of quantitative structure–activity relationship models

Guha

2008

J Comput Aided Mol Des

View full text Add to dashboard Cite

The goal of a quantitative structure-activity relationship (QSAR) model is to encode the relationship between molecular structure and biological activity or physical property. Based on this encoding, such models can be used for predictive purposes. Assuming the use of relevant and meaningful descriptors, and a statistically significant model, extraction of the encoded structure-activity relationships (SARs) can provide insight into what makes a molecule active or inactive. Such analyses by QSAR models are useful in a number of scenarios, such as suggesting structural modifications to enhance activity, explanation of outliers and exploratory analysis of novel SARs. In this paper we discuss the need for interpretation and an overview of the factors that affect interpretability of QSAR models. We then describe interpretation protocols for different types of models, highlighting the different types of interpretations, ranging from very broad, global, trends to very specific, case-by-case, descriptions of the SAR, using examples from the training set. Finally, we discuss a number of case studies where workers have provide some form of interpretation of a QSAR model.

show abstract

Section: Interpretation Methodologiesmentioning

confidence: 99%

On the interpretation and interpretability of quantitative structure–activity relationship models

Guha

2008

J Comput Aided Mol Des

View full text Add to dashboard Cite

show abstract

“…However, Naïve Bayes algorithm is unable to consider dependent attributes in its structure. MLP and RBF classifiers are multi-layer neural networks and they are not capable in generating if-then rules directly, and so they need some other interpretations to generate rules [31]. By analyzing capabilities of different learning techniques for the aim of this paper, mentioned algorithms correspond to the best ones for classification according to accident severity on this database [32].…”

Section: A Classification Of Accident Severitymentioning

confidence: 99%

A Rule-Based Decision Support System in Intelligent Hazmat Transportation System

Asadi

Ghatee

2015

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

This paper develops a new rule-based decision support system (RB-DSS) to find the safest solutions for routing, scheduling, and assignment in Hazmat transportation management. To define the safe program in RB-DSS, the accident frequency and severity are estimated for different scenarios of transportation, and they are used to classify the scenarios by a new structure of decision tree (DT), which is proposed to select branching variables at the primary levels according to the experts' perception. The outputs of the DT are stated in the form of if-then rules trained by a multilayer perceptron neural network to generalize the safe programs for Hazmat transportation. To illustrate the performance of this approach, the UK road accident data set is used.

show abstract

“…Decision trees are often combined with neural networks in both pedagogical and decompositional rule extraction approaches [273] [283]. In the decompositional approach proposed in [273], neural networks are first trained to extract the essential relationship between the input and the output.…”

Section: Rule Extraction Based On Neural Network Classifiersmentioning

confidence: 99%

“…In contrast, the decompositional algorithms consider each unit in a learning model and unify them into the rules corresponding to the model. Compared with the former algorithms, the latter ones can utilize each single unit of trained models, and can obtain detailed rules [273]. The eclectic approach [9] is a combination of the above two categories (Fig.…”

Section: Introductionmentioning

confidence: 99%