Distance-based classifiers can be re-expressed as a neural network with linear detection and nonlinear pooling layers, enabling direct application of LRP-style explanations that outperform several baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structures
Distance-based classifiers can be re-expressed as a neural network with linear detection and nonlinear pooling layers, enabling direct application of LRP-style explanations that outperform several baselines.