Redirigiendo al acceso original de articulo en 15 segundos...
Inicio  /  Information  /  Vol: 9 Par: 3 (2018)  /  Artículo
ARTÍCULO
TITULO

Residual Recurrent Neural Networks for Learning Sequential Representations

Boxuan Yue    
Junwei Fu and Jun Liang    

Resumen

Recurrent neural networks (RNN) are efficient in modeling sequences for generation and classification, but their training is obstructed by the vanishing and exploding gradient issues. In this paper, we reformulate the RNN unit to learn the residual functions with reference to the hidden state instead of conventional gated mechanisms such as long short-term memory (LSTM) and the gated recurrent unit (GRU). The residual structure has two main highlights: firstly, it solves the gradient vanishing and exploding issues for large time-distributed scales; secondly, the residual structure promotes the optimizations for backward updates. In the experiments, we apply language modeling, emotion classification and polyphonic modeling to evaluate our layer compared with LSTM and GRU layers. The results show that our layer gives state-of-the-art performance, outperforms LSTM and GRU layers in terms of speed, and supports an accuracy competitive with that of the other methods.

 Artículos similares

       
 
Muhammad Waseem, Ali Hasan Jaffry, Muhammad Azam, Ijaz Ahmad, Adnan Abbas and Jae-Eun Lee    
Food security for the growing global population is closely associated with the variations in agricultural yield at the regional scale. Based on this perspective, the current study was designed to determine the impacts of drought on wheat production in th... ver más
Revista: Water

 
Joseph M. Ackerson, Rushit Dave and Naeem Seliya    
Recurrent Neural Networks are powerful machine learning frameworks that allow for data to be saved and referenced in a temporal sequence. This opens many new possibilities in fields such as handwriting analysis and speech recognition. This paper seeks to... ver más
Revista: Information

 
Yen-Cheng Chu, Yun-Jie Jhang, Tsung-Ming Tai and Wen-Jyi Hwang    
The objective of this study is to present novel neural network (NN) algorithms and systems for sensor-based hand gesture recognition. The algorithms are able to classify accurately a sequence of hand gestures from the sensory data produced by acceleromet... ver más
Revista: Applied Sciences

 
Tessfu Geteye Fantaye, Junqing Yu and Tulu Tilahun Hailu    
Deep neural networks (DNNs) have shown a great achievement in acoustic modeling for speech recognition task. Of these networks, convolutional neural network (CNN) is an effective network for representing the local properties of the speech formants. Howev... ver más
Revista: Computers

 
Boxuan Yue, Junwei Fu and Jun Liang    
-
Revista: Information