The Journal of Interpretable and Explainable Machine Learning Systems is an international, peer-reviewed, open access journal published by Transparent Intelligence Publishing. The journal is dedicated to advancing research and innovation in interpretable machine learning, explainable artificial intelligence, transparent model design, and trustworthy AI systems that contribute to the development of reliable, accountable, and human-understandable machine learning technologies.
The journal focuses on the role of model transparency and explainability in developing trustworthy AI systems through interpretable-by-design architectures, post-hoc explanation methods, human-centered evaluation, and emerging interpretability techniques. Research related to responsible AI governance and the adoption, implementation, and regulation of explainable AI technologies is also encouraged, particularly when it contributes to improved transparency, accountability, and decision-making in machine learning systems.
The journal welcomes original research articles, review articles, systematic review articles, and case studies that contribute to the understanding, development, and application of interpretable and explainable machine learning technologies. Relevant studies may address theoretical advances, computational frameworks, practical implementations, and interdisciplinary approaches connecting machine learning, human-computer interaction, cognitive science, ethics, and regulatory compliance.
The scope of the journal includes, but is not limited to:
Interpretable-by-design machine learning models and transparent model architectures
Post-hoc explainability methods, feature attribution, and saliency-based techniques
Explainable artificial intelligence (XAI) frameworks and model-agnostic explanation methods
Deep learning interpretability, attention mechanisms, and representation analysis
Causal machine learning, causal discovery, and counterfactual explanation methods
Trustworthy and responsible AI, including fairness, accountability, and robustness
Human-AI interaction, explanation interfaces, and human-centered evaluation of AI systems
Uncertainty quantification, model calibration, and confidence estimation
Evaluation metrics and benchmarks for explanation quality, faithfulness, and stability
Natural language explanations and interpretable natural language processing
Interpretable computer vision and explainable image and video analysis models
Domain applications of interpretable and explainable machine learning in healthcare, finance, autonomous systems, and other high-stakes fields
Regulatory, ethical, and societal aspects of explainable AI, including AI governance and compliance
Knowledge-driven and hybrid neuro-symbolic approaches to interpretability
Model auditing, debugging, and transparency tools for machine learning systems
Cognitive and psychological foundations of human understanding of AI explanations
We particularly encourage interdisciplinary research that combines machine learning with human-computer interaction, cognitive science, ethics, and regulatory studies to address current and future challenges in AI transparency, accountability, fairness, and trustworthy decision-making.
Purely theoretical computer science or engineering studies without a clear contribution to interpretability, explainability, transparency, or trustworthy decision-making in machine learning systems are outside the scope of the journal.
Transparent Intelligence Publishing