4 papers
Recovering Nonlinear Functions of Latent Variables: A Plausible-Value Neural Network Framework
Eunjeong Song, Sehee Hong
When factor scores replace true latent scores in nonlinear prediction, measurement error attenuates the recoverable variance of any th-order component of the regression function…
Symb-xMIL: Symbolic Explanations for Multiple Instance Learning in Digital Pathology
Yanqing Luo, Julius Hense, Niklas PreniÃl +4
Explanations of multiple instance learning (MIL) models are widely used for validation and discovery in digital histopathology. Existing methods primarily rely on heatmaps that hig…
A novel approach to the relationships between data features -- based on comprehensive examination of mathematical, technological, and causal methodology
JaeHong Kim
The expansion of artificial intelligence (AI) has raised concerns about transparency, accountability, and interpretability, with counterfactual reasoning emerging as a key approach…
A novel approach to data generation in generative model
JaeHong Kim, Jaewon Shim
Variational Autoencoders (VAEs) and other generative models are widely employed in artificial intelligence to synthesize new data. However, current approaches rely on Euclidean geo…