In this article, we propose a stack autoencoder transfer learning algorithm based on the class separation and domain fusion (SAE-CSDF) to solve these problems. According to the characteristics of ...

While successful to a degree, traditional quantization methods falter when pushed to the extremes of low-bit representations, often resulting in a drastic degradation of model performance. OneBit, ...

In intelligent fault diagnosis, transfer learning can reduce the requirement of sufficient labeled data and the same data distribution. However, for the diagnosis of a new machine, there are still ...