Recurrent neural networks (RNNs) have been widely adopted in research areas concerned with sequential data, such as text, audio, and video. However, RNNs consisting of sigma cells or tanh cells are unable to learn the relevant information of input data when the input gap is large. By introducing gate functions into the cell structure, the long short-term memory (LSTM) could handle the problem of long-term dependencies well. Since its introduction, almost all the exciting results based on RNNs have been achieved by the LSTM. The LSTM has become the focus of deep learning. We review the LSTM cell and its variants to explore the learning capacity of the LSTM cell. Furthermore, the LSTM networks are divided into two broad categories: LSTM-dominated networks and integrated LSTM networks. In addition, their various applications are discussed. Finally, future research directions are presented for LSTM networks.
A novel process of friction stir brazing (FSB) for fabricating Al/steel layered composite (by multipass) and for joining Al to steel (by single pass) was proposed to avoid the wear of pin by steel, in which a tool without pin was used. FSB of 1.8-mm-thick Al sheet to steel sheet was conducted using a cylindrical tool with 20-mm diameter but without pin and using 0.1-mm-thick zinc foil as filler metal. For the rotational speed of 1500 rpm, sound joints were reliably obtained at the medium range of traverse speed of 75 to 235 mm/min, which fractured within Al parent sheet during tensile shear test. Furthermore, for peel test on the sound joints, Al and steel parent sheets tended to crack and deform, respectively. Metallographic examination showed that most Zn was extruded and the resultant interfacial structure consisted of several Al-Fe intermetallic compounds (IMCs) with a little Zn, less than 3 at. pct. The thickness of IMCs can be controlled to be less than 10 lm by properly increasing traverse speed (e.g., 150 mm/min). The metallurgical process of FSB was investigated by observing the microstructure of the longitudinal section of a friction stir brazed joint obtained by the suddenly stopping technique.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.