A generative-model-driven introspection method produces counterfactual image edits to explain deep neural network predictions on MNIST and CelebA.
Searching for exotic particles in high-energy physics with deep learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
Gradient boosted trees trained on nuclear data predict level density parameters for superheavy elements with reported standard deviations from 0.00035 to 0.73.
citing papers explorer
-
Generative Counterfactual Introspection for Explainable Deep Learning
A generative-model-driven introspection method produces counterfactual image edits to explain deep neural network predictions on MNIST and CelebA.
-
Trees and Islands -- Machine learning approach to nuclear physics
Gradient boosted trees trained on nuclear data predict level density parameters for superheavy elements with reported standard deviations from 0.00035 to 0.73.