Loss functions benchmark for brain tumour segmentation

From LRDE

Revision as of 08:24, 29 June 2020 by Bot (talk | contribs) (Created page with "{{CSIReport | authors = Lukas Rabier | title = Loss functions benchmark for brain tumour segmentation | year = 2020 | number = 2015 | abstract = Training a convolutional neura...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Abstract

Training a convolutional neural network relies on the use of loss functions, which provide an evaluation of the performance that allows the network's optimisation. Different loss functions evaluate performance in different waysand thus affect the training differently. This report aims to share our progress in evaluating the performance of various loss functions in the training of convolutional neural networks for brain tumour segmentation.