FractalNet: Ultra-Deep Neural Networks without Residuals ICLR 2017 Gustav Larsson, Michael Maire, Gregory Shakhnarovich 文章提出了什么(What) ResNet提升了深度网络的表现,本文提出的分形网络也取得了优秀的表现,通过实验表示,残差结构对于深度网络来说不是必须的。 ResNet缺乏正则方法,本文提出了drop-path,对子...
不过遗憾的是,作者提供的源码中只有Local Drop Path的实现,而并没有Global的,因此本人在该源码的基础上很难复现出论文中的结果,尤其是在作者的第二个实验中,对于深层的网络,提取出最深的路径也很难达到很好的效果,这很可能就是Global无法实现所
FractalNet: Ultra-deep neural networks without residuals. In International Conference on Learning Representations, 2017.G. Larsson, M. Maire, and G. Shakhnarovich. Fractalnet: Ultra-deep neural networks without residuals. In ICLR 2017.G. Larsson, M. Maire, and G. Shakhnarovich. Fractalnet: ...
Apply the CEEMDAN method to decompose the input data, resulting in the extraction of multiple intrinsic mode functions (IMFs) and residuals. Step 3. CNN-BiLSTM deterministic prediction. Input multiple IMFs and residuals into the CNN-BiLSTM prediction model, and superpose each predictive component ...