Deep sequence networks such as multi-head self-attention networks provide a promising
way to extract effective representations from raw sequence data in an end-to-end fashion …

Deep learning provides a promising way to extract effective representations from raw data in
an end-to-end fashion and has proven its effectiveness in various domains such as …

We consider the problem of feature extraction in ultrasound diagnosis of cirrhosis. The
classification of liver cirrhosis is mainly based on the performance of ultrasonic images of …