logo SBA

ETD

Archivio digitale delle tesi discusse presso l’Università di Pisa

Tesi etd-01192020-171633


Tipo di tesi
Tesi di laurea magistrale
Autore
SPINNATO, FRANCESCO
URN
etd-01192020-171633
Titolo
A Model Agnostic Local Explainer for Time Series Black-Box Classifiers
Dipartimento
INFORMATICA
Corso di studi
DATA SCIENCE AND BUSINESS INFORMATICS
Relatori
relatore Prof.ssa Monreale, Anna
relatore Prof. Guidotti, Riccardo
Parole chiave
  • agnostic
  • autoencoder
  • black box
  • blackbox
  • explainability
  • interpretability
  • neural network
  • shap
  • surrogate
  • time series
Data inizio appello
06/03/2020
Consultabilità
Non consultabile
Data di rilascio
06/03/2090
Riassunto
This study presents an agnostic approach to explain the predictions of time series black-box classifiers. Through an autoencoder, this method generates a local neighborhood of the instance to be explained, and then learns a local decision tree classifier to extract rules and counterfactuals. The final explanation is composed by exemplar and counterexemplar time series, and by a shapelet based verbose and graphical decision rule clarifying the black-box decision.
File