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
06 Jul 2007
TL;DR: The results show the hybrid neural network- the combination of an unsupervised self-organizing mapping network and a multilayer perception network with error back- propagation algorithm is capable to produce good performance without labels by small training set.
Abstract: Classification of breast tumors through the contour complexity parameter estimated by divider-step method was studied, using a hybrid neural network- the combination of an unsupervised self-organizing mapping network (SOM) and a multilayer perception (MLP) network with error back- propagation (BP) algorithm. The SOM was used to identify clusters and their centers in data (259 cases). Two-cluster data was then obtained by K-Nearest Neighbor. A profile for each cluster was determined by specified distance from its center. The cluster "profile" provided typical cases in the cluster and was applied to BP-ANN as the training set. The 96% specificity at 91.8% sensitivity was achieved after training. The results show the hybrid neural network is capable to produce good performance without labels by small training set.
4 citations
TL;DR: Zhang et al. as discussed by the authors proposed an end-to-end EFI model considering different event-related sources, which constructs the candidate event sets from raw texts to capture various kinds of eventrelated information, and then proposes a hybrid neural network model on GCN and BiLSTM to learn semantic and syntactic features, respectively.
Abstract: Event factuality identification (EFI) is a task to judge the factuality of events in texts, and is also the basic task of many related applications in the field of Natural Language Processing (NLP), such as information extraction and rumor detection. Previous research on EFI relied on annotated information, which cannot be applied to real world applications directly, and some studies only considered the default source AUTHOR. To address the above issues, this paper launches an end-to-end EFI model considering different event-related sources, which constructs the candidate event sets from raw texts to capture various kinds of event-related information, and then proposes a hybrid neural network model on GCN and BiLSTM to learn semantic and syntactic features, respectively. The experimental results on FactBank show that our proposed approach outperforms the baselines.
4 citations
TL;DR: A dynamic cluster model based on hybrid NN optimization is proposed along with the Gaussian copula technique for realizing the correlation between the clusters for efficient cooperative communication and results show that the model maximizes the amount of information in the cluster and balances the resource allocation among nodes to improve the life of the entire network.
Abstract: The internet-of-things(IoT) extends the traditional Internet and realizes the interconnection of all things in a smart way. With the rapid development of 5G and beyond communication technology, the number of users and demands for IoT applications has increased significantly along with resource constraints networking in the communication systems. The next generation IoT applications challenges these issue using smarter cooperative communication with large heterogeneous clusters along in par with traditional IoT systems. The proposed work illustrates a hybrid neural network (NN) model for dynamic clustering for efficient next generation IoT applications. A dynamic cluster model based on hybrid NN optimization is proposed along with the Gaussian copula technique for realizing the correlation between the clusters for efficient cooperative communication. The mathematical analysis and simulation results show that the model maximizes the amount of information in the cluster and balances the resource allocation among nodes to improve the life of the entire network.
4 citations
01 Jan 1998
TL;DR: This chapter Marina Resta demonstrates experimentally the great potential of neural networks for design of systems for trading stock markets by suggesting the use of a hybrid neural network architecture that combines the approach of Self-Organizing Maps together with that of Genetic Algorithms.
Abstract: In this chapter Marina Resta demonstrates experimentally the great potential of neural networks for design of systems for trading stock markets. She suggests the use of a hybrid neural network architecture that combines the approach of Self-Organizing Maps together with that of Genetic Algorithms. She shows the forecasting capabilities of this hybrid system and evidence of the performance of this system. This chapter is a nice extension of the applications of trading systems presented in “Trading on the Edge”. The novelty here is that genetic algorithms and self-organizing maps are combined.
4 citations
13 Sep 1993
TL;DR: In this paper, four working conditions of a control system are simulated, one normal and three abnormal — hysteresis at a valve, systematic deviation on the output of the measurement device and an abnormal amount of noise on the measurement devices output.
Abstract: In this paper we simulated four working conditions of a control system, one normal and three abnormal — hysteresis at a valve, systematic deviation on the output of the measurement device and an abnormal amount of noise on the measurement device output. The monitoring system was build to distinguish these four conditions. The information available for the system consists of the set point, the measurement and the controller output.
4 citations