Highly interpretable hierarchical deep rule-based classifier

Abstract

Deep learning paradigm is arguably the fastest growing branch of machine learning and artificial intelligence (AI) at the moment [1,2]. Deep neural networks (DNNs) are entirely based on the artificial neural networks and probabilistic type of uncertainties [3]. They have demonstrated eye-catching successes on image classification [4,5], speech processing [6,7] and many other complex problems [8,9] that traditional machine learning approaches are struggling with.Despite of the impressive advances DNNs have achieved, the research communities and enterprises are increasingly demanding explainable AI [10,11]. Indeed, DNN-based AI algorithms nowadays are more frequently getting involved for making decisions in financial and safety-critical applications [12,13]. However, DNNs are the typical type of "black box" models with a very high level of complexity level that only computers can understand. It is reported that such "black box" models can provide a wrong outcome with high confidence by modifying just one pixel in the input images [14]. The lack of transparency and explainability can pose a significant obstacle, especially for highly regulated, high-risk/high-value industries. Therefore, there is a high demand in developing alternative architectures, learning and model structure paradigms that can provide offer [15]: (1) high levels of precision comparable or surpassing the level achieved by humans or/and by the state-of-the-art methods (including DNNs); (2) be highly transparent, interpretable, easy to explain and use for humans; (3) computationally efficient, fast to train and use; (4) computational resource and training data lean -able to be trained with a single or handful or examples per class, not requiring computer accelerators, such as GPU, HPC, etc.As one of the pillars of the computational intelligence, fuzzy rule-based (FRB) systems are a mathematical tool to describe the human reasoning and decision-making processes [11]. FRB systems take the form of zero-order, Highly interpretable hierarchical deep rule-based classifierXiaowei Gu a, b, ⁎, 1

Automatic Fuzzy Graph Construction For Interpretable Image Classification

“…Recently proposed approaches provide interpretable results based on features extracted by CNNs. Such type of models is the Deep Rule-Based (DRB) [10] model that combined the zero-order selforganizing fuzzy rule-based system with a multi-layer imageprocessing architecture, as well as, the Hierarchical DRB (H-DRB) [11] that consisted an evolution of DRB. Other interpretable image classification approaches, such as the Interpretable Deep Neural Networks (xDNN) [13], utilized image samples, for the learning of the classification rules.…”

A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Data

“…To solve this deficiency, multiple strategies are proposed in a research domain commonly referred to as 'eXplainable AI' (XAI) [15], aimed at unveiling the high complexity of the models obtained through machine learning methodologies as deep neural networks [16,17], ensemble methods [18,19], and support vector machines [20]. They also have vast application in various fields, including finance [21,22], medicine [23,24], and self-driving cars [25,26].…”

A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Data

“…To solve this deficiency, multiple strategies are proposed in a research domain commonly referred to as 'eXplainable AI' (XAI) [37], aimed at unveiling the high complexity of the models obtained through machine learning methodologies as deep neural networks [63,20], ensemble methods [23,57] and support vector machines [6]. They also have vast application in various fields, including finance [32,12], medicine [58,22] and self-driving cars [68,40].…”