Principles and Practice of Explainable Machine Learning

Abstract Artificial intelligence (AI) provides many opportunities to improve private and public life. Discovering patterns and structures in large troves of data in an automated manner is a core component of data science, and currently drives applications in diverse areas such as computational biology, law and finance. However, such a highly positive impact is coupled with a significant challenge

Abstract Artificial intelligence (AI) provides many opportunities to improve private and public life. Discovering patterns and structures in large troves of data in an automated manner is a core component of data science, and currently drives applications in diverse areas such as computational biology, law and finance. However, such a highly positive impact is coupled with a significant challenge: how do we understand the decisions suggested by these systems in order that we can trust them? In this report, we focus specifically on data-driven methods—machine learning (ML) and pattern…

related reading

• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
• Understanding Explainable AIforbes.com
• Against Interpretability: a Critical Examination of the Interpretability Problem in Machine Learninglink.springer.com
• [2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
• Shapley value: from cooperative game to explainable artificial intelligence | Autonomous Intelligent Systems | Springer Nature Linklink.springer.com
• The necessity of machine learning theory in mitigating AI riskmishabelkin.substack.com
• Deep Learning is Not So Mysterious or Differentarxiv.org
• A Course in Machine Learningciml.info
• Training Language Models to Explain Their Own Computationsarxiv.org
• On Optimism for Interpretabilitygoodfire.ai
• 2 Interpretability – Interpretable Machine Learningchristophm.github.io