"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Почему я должен вам доверять?
2016-08-08
SCID: 54.1/m5w6g3zc
Discuss with AI
black-box modelsmodel interpretabilitymodel transparencyprediction explanationstrustworthy machine learning
Figures from the paper
Abstract (AI)
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one.
Key Findings
1
Explanations of predictions can provide insights into model behavior and help identify ways to transform untrustworthy models or predictions into trustworthy ones.
2
The abstract highlights the opacity of widely adopted machine-learning models as a central challenge to trust and deployment decisions.
3
Understanding the reasons behind machine-learning predictions is important for assessing trust before acting on predictions or deploying models.
Research Object
Machine learning models and their predictions
Research Subject
Interpretability of model predictions as a basis for assessing and improving trustworthiness and deployment decisions
Publication Details
Publication Date
2016-08-08
Journal
Publisher
ISSN
Cited by
28124
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai3
Cited by20
A Unified Approach to Interpreting Model Predictions2017
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions2021
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)2018
EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces2018
Deep learning for healthcare: review, opportunities and challenges2017
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence2023
A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI2020
Causability and explainability of artificial intelligence in medicine2019
Time-series forecasting with deep learning: a survey2021
Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence2023
Machine Learning Interpretability: A Survey on Methods and Metrics2019
Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey2023
Explainable Machine Learning for Scientific Insights and Discoveries2020
Artificial intelligence in the construction industry: A review of present status, opportunities and future challenges2021
Bias in data‐driven artificial intelligence systems—An introductory survey2020
Machine Learning and Deep Learning Methods for Intrusion Detection Systems: A Survey2019
Deep learning in cancer diagnosis, prognosis and treatment selection2021
A Unifying Review of Deep and Shallow Anomaly Detection2021
A Survey on the Explainability of Supervised Machine Learning2021
Questioning the AI: Informing Design Practices for Explainable AI User Experiences2020