Continual Learning by Three-Phase Consolidation

Maltoni, Davide, Pellegrini, Lorenzo

arXiv.org Artificial Intelligence 

TPC (Three-Phase Consolidation) is here introduced as a simple but effective approach to continually learn new classes (and/or instances of known classes) while controlling forgetting of previous knowledge. Each experience (a.k.a. task) is learned in three phases characterized by different rules and learning dynamics, aimed at removing the class-bias problem (due to class unbalancing) and limiting gradient-based corrections to prevent forgetting of underrepresented classes. Several experiments on complex datasets demonstrate its accuracy and efficiency advantages over competitive existing approaches. The algorithm and all the results presented in this paper are fully reproducible thanks to its publication on the Avalanche open framework for continual learning.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found