Topic
Hybrid neural network
About: Hybrid neural network is a research topic. Over the lifetime, 1305 publications have been published within this topic receiving 18223 citations.
Papers published on a yearly basis
Papers
More filters
••
25 May 2016TL;DR: This work presents the adapted hybrid neural network (HDNN) in which the last layers are divided into several blocks of variable size so that the network could extract features of different scales.
Abstract: Detecting small objects such as vehicles in aerial images is a complicated problem, because it is difficult or impossible to find a suitable feature space to solve the problem for small objects. The aim of this work is to develop a system capable in real-time to solve the challenge of detection the vehicles. Deep convolutional networks can automatically extract rich features from the training sample and achieve good performance on a variety of data. In this paper, we present the adapted hybrid neural network (HDNN) in which the last layers are divided into several blocks of variable size so that the network could extract features of different scales. Experimental results show that HDNN, which was offered, exceeds the results of other conventional transport methods of detection.
31 citations
••
TL;DR: The experimental results show that the hybrid neural network has a stronger historical learning ability than two other widely used recurrent neural networks and can effectively reduce the number of iterations required by the recurrent neural network, thereby reducing the overall learning time.
Abstract: Seeking to address the challenges associated with high-dimensional complex time series representations of recurrent neural networks, such as low generalization ability and long training time, a hybrid neural network based on a deep belief network (DBN) is proposed in this paper to facilitate time series predictions for the Internet of Things. In our approach, we integrate both a DBN and a recurrent neural network with the gated recurrent unit as the activation unit. First, we implement unsupervised pretraining through the DBN and then supervise the curve fitting using the recurrent neural network. Finally, the hybrid neural network is learned and can make predictions. The experimental results show that the hybrid neural network has a stronger historical learning ability than two other widely used recurrent neural networks and can effectively reduce the number of iterations required by the recurrent neural network, thereby reducing the overall learning time.
31 citations
••
TL;DR: The result shows that the CNN-LSTM hybrid neural network can effectively improve the accuracy of value prediction and direction prediction compared with the single structure neural network.
Abstract: In this study, aiming at the problem that the price of Bitcoin varies greatly and is difficult to predict, a hybrid neural network model based on convolutional neural network (CNN) and long short-term memory (LSTM) neural network is proposed. The transaction data of Bitcoin itself, as well as external information, such as macroeconomic variables and investor attention, are taken as input. Firstly, CNN is used for feature extraction. Then the feature vectors are input into LSTM for training and forecasting the short-term price of Bitcoin. The result shows that the CNN-LSTM hybrid neural network can effectively improve the accuracy of value prediction and direction prediction compared with the single structure neural network. The finding has important implications for researchers and investors in the digital currencies market.
31 citations
••
TL;DR: In this article, a hybrid neural network was proposed for the accurate estimation of blood pressure (BP) using only non-invasive electrocardiogram (ECG) and photoplethysmogram (PPG) waveforms as inputs.
30 citations
••
TL;DR: In this article, a hybrid technique is proposed, using the time series generated by the individual models as inputs of a new ANN, which aims to increase the accuracy of the simulated flow by combining and exploiting the information provided by physical and data-driven models.
30 citations