Avancerad sökning

Hittade 1 uppsats som matchar ovanstående sökkriterier.

1. 1. Avoiding Catastrophic Forgetting in Continual Learning through Elastic Weight Consolidation

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Anton Evilevitch; Robert Ingram; [2021]
   Nyckelord :Image classification; DenseNet; Elastic Weight Consolidation; Catastrophic Forgetting; CIFAR100; Bildklassifiering; DenseNet; Elastic Weight Consolidation; Catastrophic Forgetting; CIFAR100;

   Sammanfattning : Image classification is an area of computer science with many areas of application. One key issue with using Artificial Neural Networks (ANN) for image classification is the phenomenon of Catastrophic Forgetting when training tasks sequentially (i.e Continual Learning). LÄS MER