arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.09697cs.LG
收藏

技术报告:结合培训期间的迁移学习知识和Wide Resnets

Technical Report: Combining knowledge from Transfer Learning during training and Wide Resnets

Wolfgang Fuhl

摘要:

在这份报告中,我们结合了Wide ResNets和迁移学习的思想来优化深度神经网络的架构。该体系结构的第一个改进是使用所有层作为最后一层的信息源。这个想法来自迁移学习,它使用在其他数据上预先训练的网络,并提取网络的不同级别作为新任务的输入。第二个改进是使用更深的层,而不是更深的块序列。这个想法来自Wide ResNets。使用这两种优化,高数据增强和标准数据增强都可以为不同的模型产生更好的结果。链接:https://github.com/wolfgangfuhl/PublicationStuff/tree/master/TechnicalReport1/Supp

英文摘要:

In this report, we combine the idea of Wide ResNets and transfer learning to optimize the architecture of deep neural networks. The first improvement of the architecture is the use of all layers as information source for the last layer. This idea comes from transfer learning, which uses networks pre-trained on other data and extracts different levels of the network as input for the new task. The second improvement is the use of deeper layers instead of deeper sequences of blocks. This idea comes from Wide ResNets. Using both optimizations, both high data augmentation and standard data augmentation can produce better results for different models. Link: https://github.com/wolfgangfuhl/PublicationStuff/tree/master/TechnicalReport1/Supp

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑