Explaining black-box deep neural models' predictions, behaviors, and performances through the unsupervised mining of their inner knowledge
Year: 2021
Type: dissertation
Abstract: Relative size of the features extracted with MLWE strategy (i.e.size of the most influential clusters of words) for all the informative local explanations.The relative size is calculated, for each local explanation, as the number of tokens in the cluster over the number of tokens in the input text. . . . . . . . . . . . . .
Source: PORTO@Iris
Author: Francesco Ventura
Institution: Politecnico di Torino
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3184443165
