Difference between revisions of "Publications/rabier.20.seminar"
From LRDE
(Created page with "{{CSIReport | authors = Lukas Rabier | title = Loss functions benchmark for brain tumour segmentation | year = 2020 | number = 2015 | abstract = Training a convolutional neura...") |
|||
Line 4: | Line 4: | ||
| year = 2020 |
| year = 2020 |
||
| number = 2015 |
| number = 2015 |
||
− | | 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 |
+ | | 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 ways, and 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. |
| type = techreport |
| type = techreport |
||
| id = rabier.20.seminar |
| id = rabier.20.seminar |
Latest revision as of 17:23, 9 November 2020
- Authors
- Lukas Rabier
- Type
- techreport
- Year
- 2020
- Number
- 2015
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 ways, and 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.