Papers of the day   All papers

Interpretable Machine Learning – A Brief History, State-of-the-Art and Challenges

Comments

Christoph Molnar: We have a new paper on arxiv 🎉🎉 Interpretable Machine Learning - A Brief History, State-of-the-Art and Challenges. Best to read in a comfortable chair with a cup of coffee/tea. It's an extended abstract to a keynote I gave at the ECML XKDD workshop. https://arxiv.org/abs/2010.09337

19 replies, 888 likes


elvis: The future of machine learning and its adoption in the real world relies on being able to better understand how models make predictions, especially in heavily regulated domains. Take a look at this paper on interpretable ML to better understand this area of study and challenges.

0 replies, 49 likes


Javier Nogales: This paper helps to shed some light on interpretation of (black box) machine-learning tools Overview and history of #IML: https://arxiv.org/pdf/2010.09337.pdf #datascience https://t.co/hE9PSYPgBk

0 replies, 6 likes


Bhagirath Kumar Lader: Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges Christoph Molnar, Giuseppe Casalicchio, Bernd Bischl #machinelearning #deeplearning #art #artificialintelligence #AI #XAI https://arxiv.org/abs/2010.09337

0 replies, 1 likes


Content

Found on Oct 20 2020 at https://arxiv.org/pdf/2010.09337.pdf

PDF content of a computer science paper: Interpretable Machine Learning – A Brief History, State-of-the-Art and Challenges