Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI

Classification is one of the most active research and application areas of neural networks. The literature is vast and growing. This paper summarizes some of the most important developments in neural network classification research. Specifically, the issues of posterior probability estimation, the link between neural and conventional classifiers, learning and generalization tradeoff in classification, the feature variable selection, as well as the effect of misclassification costs are examined. Our purpose is to provide a synthesis of the published research in this area and stimulate further research interests and efforts in the identified topics.

/pdf/neural-networks-for-classification-a-survey-573tgz3hdm.pdf

Neural networks for classification: a survey

In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI.

http://www.biospec.net/learning/Metab06/Goodacre-TibTech.pdf

Metabolomics by numbers: acquiring and understanding global metabolite data.

Image processing with neural networks–a review

To date, the preponderance of techniques for eliciting the knowledge embedded in trained artificial neural networks (ANN's) has focused primarily on extracting rule-based explanations from feedforward ANN's. The ADT taxonomy for categorizing such techniques was proposed in 1995 to provide a basis for the systematic comparison of the different approaches. This paper shows that not only is this taxonomy applicable to a cross section of current techniques for extracting rules from trained feedforward ANN's but also how the taxonomy can be adapted and extended to embrace a broader range of ANN types (e,g., recurrent neural networks) and explanation structures. In addition we identify some of the key research questions in extracting the knowledge embedded within ANN's including the need for the formulation of a consistent theoretical basis for what has been, until recently, a disparate collection of empirical results.

The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks

A recognized impediment to the more widespread utilization of artificial neural networks (ANNs) is the absence of a capability to explain, in a human-comprehensible form, either the process by which a trained ANN arrives at a specific decision/result or, in general, the totality of knowledge embedded therein. There has been a proliferation of techniques aimed at redressing this situation and, in particular, for extracting the knowledge embedded in trained feedforward ANNs as sets of symbolic rules. However, if the dissemination of ideas in the field of ANN rule extraction is to proceed in a systematic manner, then it is essential that a rigorous taxonomy exists for categorizing the plethora of techniques being developed. This paper shows how one of the proposed schemas for categorizing ANN rule extraction techniques is able to accommodate such developments in the field. In addition attention is drawn to what are seen to be some of the key challenges in the area including the identification of factors which appear to limit what is actually achievable through the rule extraction process.

M. Golea

Papers

The truth will come to light: directions and challenges in extracting the knowledge embedded within trained artificial neural networks

The truth is in there: current issues in extracting rules from trained feedforward artificial neural networks