Interpretability research of deep learning: A literature survey
B Xua, G Yang - Information Fusion, 2024 - Elsevier
Deep learning (DL) has been widely used in various fields. However, its black-box nature
limits people's understanding and trust in its decision-making process. Therefore, it becomes …
limits people's understanding and trust in its decision-making process. Therefore, it becomes …
Is Machine Learning Unsafe and Irresponsible in Social Sciences? Paradoxes and Reconsidering from Recidivism Prediction Tasks
J Liu, D Li - ar** machine learning classifiers can exhibit biases against
specific protected attributes. Such biases typically originate from historical discrimination or …
specific protected attributes. Such biases typically originate from historical discrimination or …
Learning Fair Policies for Multi-Stage Selection Problems from Observational Data
We consider the problem of learning fair policies for multi-stage selection problems from
observational data. This problem arises in several high-stakes domains such as company …
observational data. This problem arises in several high-stakes domains such as company …
Harnessing coloured petri nets to enhance machine learning: A simulation-based method for healthcare and beyond
Abstract Many industries use Machine Learning (ML) techniques to enhance systems'
performance. However, integrating ML into these systems poses challenges, often requiring …
performance. However, integrating ML into these systems poses challenges, often requiring …
Balancing Predictive Performance and Interpretability in Machine Learning: A Scoring System and an Empirical Study in Traffic Prediction
This paper investigates the empirical relationship between predictive performance, often
called predictive power, and interpretability of various Machine Learning algorithms …
called predictive power, and interpretability of various Machine Learning algorithms …
Towards Trustworthy and Reliable AI: The Next Frontier
S Akhai - Explainable Artificial Intelligence (XAI) in Healthcare, 2024 - taylorfrancis.com
This chapter discusses the importance of AI interpretability in various domains, highlighting
its need for transparency and explainability. It categorizes AI interpretability strategies into …
its need for transparency and explainability. It categorizes AI interpretability strategies into …
Learning Optimal Classification Trees Robust to Distribution Shifts
We consider the problem of learning classification trees that are robust to distribution shifts
between training and testing/deployment data. This problem arises frequently in high stakes …
between training and testing/deployment data. This problem arises frequently in high stakes …
Fair and Accurate Regression: Strong Formulations and Algorithms
This paper introduces mixed-integer optimization methods to solve regression problems that
incorporate fairness metrics. We propose an exact formulation for training fair regression …
incorporate fairness metrics. We propose an exact formulation for training fair regression …