Machine learning interpretability: A survey on methods and metrics
DV Carvalho, EM Pereira, JS Cardoso - Electronics, 2019 - mdpi.com
Machine learning systems are becoming increasingly ubiquitous. These systems's adoption
has been expanding, accelerating the shift towards a more algorithmic society, meaning that …
has been expanding, accelerating the shift towards a more algorithmic society, meaning that …
Does the whole exceed its parts? the effect of ai explanations on complementary team performance
Many researchers motivate explainable AI with studies showing that human-AI team
performance on decision-making tasks improves when the AI explains its recommendations …
performance on decision-making tasks improves when the AI explains its recommendations …
Peeking inside the black-box: a survey on explainable artificial intelligence (XAI)
At the dawn of the fourth industrial revolution, we are witnessing a fast and widespread
adoption of artificial intelligence (AI) in our daily life, which contributes to accelerating the …
adoption of artificial intelligence (AI) in our daily life, which contributes to accelerating the …
Is there a trade-off between fairness and accuracy? a perspective using mismatched hypothesis testing
A trade-off between accuracy and fairness is almost taken as a given in the existing literature
on fairness in machine learning. Yet, it is not preordained that accuracy should decrease …
on fairness in machine learning. Yet, it is not preordained that accuracy should decrease …
Is Our Continual Learner Reliable? Investigating Its Decision Attribution Stability through SHAP Value Consistency
Y Cai, S Ling, L Zhang, L Pan… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
In this work we identify continual learning (CL) methods' inherent differences in sequential
decision attribution. In the sequential learning process inconsistent decision attribution may …
decision attribution. In the sequential learning process inconsistent decision attribution may …
Globally optimal score-based learning of directed acyclic graphs in high-dimensions
We prove that $\Omega (s\log p) $ samples suffice to learn a sparse Gaussian directed
acyclic graph (DAG) from data, where $ s $ is the maximum Markov blanket size. This …
acyclic graph (DAG) from data, where $ s $ is the maximum Markov blanket size. This …
A study on labeling network hostile behavior with intelligent interactive tools
Labeling a real network dataset is specially expensive in computer security, as an expert
has to ponder several factors before assigning each label. This paper describes an …
has to ponder several factors before assigning each label. This paper describes an …
On mismatched detection and safe, trustworthy machine learning
KR Varshney - 2020 54th Annual Conference on Information …, 2020 - ieeexplore.ieee.org
Instilling trust in high-stakes applications of machine learning is becoming essential. Trust
may be decomposed into four dimensions: basic accuracy, reliability, human interaction, and …
may be decomposed into four dimensions: basic accuracy, reliability, human interaction, and …
Enhancing simple models by exploiting what they already know
A Dhurandhar, K Shanmugam… - … Conference on Machine …, 2020 - proceedings.mlr.press
There has been recent interest in improving performance of simple models for multiple
reasons such as interpretability, robust learning from small data, deployment in memory …
reasons such as interpretability, robust learning from small data, deployment in memory …
Interpretable deep learning for monitoring combustion instability
Transitions from stable to unstable states occurring in dynamical systems can be sudden
leading to catastrophic failure and huge revenue loss. For detecting these transitions during …
leading to catastrophic failure and huge revenue loss. For detecting these transitions during …