Results 1 to 10 of about 1,818,152 (349)
Explainable AI: A Review of Machine Learning Interpretability Methods
Entropy, 2020 Recent advances in artificial intelligence (AI) have led to its widespread industrial adoption, with machine learning systems demonstrating superhuman performance in a significant number of tasks.
Pantelis Linardatos +2 more
doaj +2 more sources
Interpretable deep learning: interpretation, interpretability, trustworthiness, and beyond [PDF]
Knowledge and Information Systems, 2022 Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-box nature, it is often difficult to understand the prediction results of deep models.
Li, Xuhong +7 more
openaire +3 more sources
Progress measures for grokking via mechanistic interpretability [PDF]
International Conference on Learning Representations, 2023 Neural networks often exhibit emergent behavior, where qualitatively new capabilities arise from scaling up the amount of parameters, training data, or training steps.
Neel Nanda +4 more
semanticscholar +1 more source
Towards Automated Circuit Discovery for Mechanistic Interpretability [PDF]
Neural Information Processing Systems, 2023 Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpretability process they followed.
Arthur Conmy +4 more
semanticscholar +1 more source
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small [PDF]
International Conference on Learning Representations, 2022 Research in mechanistic interpretability seeks to explain behaviors of machine learning models in terms of their internal components. However, most previous work either focuses on simple behaviors in small models, or describes complicated behaviors in ...
Kevin Wang +4 more
semanticscholar +1 more source
An Identification Method of Feature Interpretation for Melanoma Using Machine Learning
Applied Sciences, 2023 Melanoma is a fatal skin cancer that can be treated efficiently with early detection. There is a pressing need for dependable computer-aided diagnosis (CAD) systems to address this concern effectively.
Zhenwei Li +4 more
doaj +1 more source
The mythos of model interpretability [PDF]
Queue, 2016 In machine learning, the concept of interpretability is both important and slippery.
Zachary Chase Lipton
semanticscholar +1 more source
Macroeconomic Predictions Using Payments Data and Machine Learning
Forecasting, 2023 This paper assesses the usefulness of comprehensive payments data for macroeconomic predictions in Canada. Specifically, we evaluate which type of payments data are useful, when they are useful, why they are useful, and whether machine learning (ML ...
James T. E. Chapman, Ajit Desai
doaj +1 more source
XAI for Churn Prediction in B2B Models: A Use Case in an Enterprise Software Company
Mathematics, 2022 The literature related to Artificial Intelligence (AI) models and customer churn prediction is extensive and rich in Business to Customer (B2C) environments; however, research in Business to Business (B2B) environments is not sufficiently addressed ...
Gabriel Marín Díaz +2 more
doaj +1 more source
A Double Penalty Model for Ensemble Learning
Mathematics, 2022 Modern statistical learning techniques often include learning ensembles, for which the combination of multiple separate prediction procedures (ensemble components) can improve prediction accuracy.
Wenjia Wang, Yi-Hui Zhou
doaj +1 more source