Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 1
Rule extraction from deep neural networks
Urška Matjašec, Aleksander Sadikov, Mateja Jamnik, Zohreh Shams
Magistrsko delo
Oznake: explainability of neural networks;deep feedforward neural networks;rule extraction;decision rules;decompositional algorithm;
Despite their high accuracy, deep neural networks’ main disadvantage is their lack of transparency, interpretability and explainability. This has prevented them from being widely used in safety and security critical systems, for example, healthcare. There have been many attempts to interpret neural ...
Leto: 2020 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Št. zadetkov: 1
Ključne besede:
Leto izdaje:
Avtorji:
Repozitorij:
Tipologija:
Jezik: