DeepAI AI Chat
Log In Sign Up

Towards Quantification of Explainability in Explainable Artificial Intelligence Methods

by   Sheikh Rabiul Islam, et al.

Artificial Intelligence (AI) has become an integral part of domains such as security, finance, healthcare, medicine, and criminal justice. Explaining the decisions of AI systems in human terms is a key challenge–due to the high complexity of the model, as well as the potential implications on human interests, rights, and lives . While Explainable AI is an emerging field of research, there is no consensus on the definition, quantification, and formalization of explainability. In fact, the quantification of explainability is an open challenge. In our previous work, we incorporated domain knowledge for better explainability, however, we were unable to quantify the extent of explainability. In this work, we (1) briefly analyze the definitions of explainability from the perspective of different disciplines (e.g., psychology, social science), properties of explanation, explanation methods, and human-friendly explanations; and (2) propose and formulate an approach to quantify the extent of explainability. Our experimental result suggests a reasonable and model-agnostic way to quantify explainability


page 1

page 2

page 3

page 4


A Theoretical Framework for AI Models Explainability

Explainability is a vibrant research topic in the artificial intelligenc...

On Explainability in AI-Solutions: A Cross-Domain Survey

Artificial Intelligence (AI) increasingly shows its potential to outperf...

A Taxonomy of Explainable Bayesian Networks

Artificial Intelligence (AI), and in particular, the explainability ther...

Explainability in reinforcement learning: perspective and position

Artificial intelligence (AI) has been embedded into many aspects of peop...

Deep Learning Generates Synthetic Cancer Histology for Explainability and Education

Artificial intelligence (AI) methods including deep neural networks can ...

Social Construction of XAI: Do We Need One Definition to Rule Them All?

There is a growing frustration amongst researchers and developers in Exp...