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
Posted Content•
TL;DR: This work investigates whether the watchdog should be separate from the neural network or symbiotically attached, and presents empirical evidence that the symbiotic watchdog performs better than when the neural networks are disjoint.
Abstract: Neural networks are largely black boxes. A neural network trained to classify fruit may classify a picture of a giraffe as a banana. A neural network watchdog's job is to identify such inputs, allowing a classifier to disregard such data. We investigate whether the watchdog should be separate from the neural network or symbiotically attached. We present empirical evidence that the symbiotic watchdog performs better than when the neural networks are disjoint.
2 citations
01 Jan 1997
2 citations
01 Jul 2017
TL;DR: Experimental results show that the best accuracy belongs to different hybrid models on different sub-datasets, which indicate the proposed approach can make use of each models advantages aim at different sub thedataset.
Abstract: With the rise and popular of artificial intelligence,the technology of conversation between human and machine get more and more attention. Using neural network model on the Encoder-Decoder framework has been wildly used in translation and human-machine conversation. This paper we propose a new hybrid neural network model (HNN) which consists of some essential neural network models (that is RNN, LSTM, and CNN). At the same time, according to the number of words that each sentence contains, we will get three sub-datasets from the original dataset. Then training and testing our models on different sub-datasets. Experimental results show that the best accuracy belongs to different hybrid models on different sub-datasets, which indicate the proposed approach can make use of each models advantages aim at different sub-dataset.
2 citations
TL;DR: A long short-term memory-residual model that captures the time-domain and morphological ECG signal information simultaneously and fuses the two information types and demonstrates that the proposed method is an efficient automated detection method.
Abstract: Arrhythmia is a common cardiovascular disease; the electrocardiogram (ECG) is widely used as an effective tool for detecting arrhythmia. However, real-time arrhythmia detection monitoring is difficult, so this study proposes a long short-term memory-residual model. Individual beats provide morphological features and combined with adjacent segments provide temporal features. Our proposed model captures the time-domain and morphological ECG signal information simultaneously and fuses the two information types. At the same time, the attention block is applied to the network to further strengthen the useful information, capture the hidden information in the ECG signal, and improve the model classification performance. Our model was finally trained and tested on the MIT-BIH arrhythmia database, and the entire dataset was divided into intrapatient and interpatient modes. Accuracies of 99.11% and 85.65%, respectively, were obtained under the two modes. Experimental results demonstrate that our proposed method is an efficient automated detection method.
2 citations
28 Jun 2000
TL;DR: The fuzzy identification proposed by Takaki and Sugeno (1985) is extended to a MIMO adaptive controller based on a hybrid neural network structure that can be adjusted by the extended Bp algorithm to realize automatic rule modification.
Abstract: The fuzzy identification proposed by Takaki and Sugeno (1985) is extended to a MIMO adaptive controller based on a hybrid neural network structure. The network is roughly divided into the premise and consequence corresponding to the T-S model. Each parameter of the consequence function can be adjusted by the extended Bp algorithm so that automatic rule modification can be realized. The membership function of each fuzzy subset can be modified by a genetic algorithm. In this way, more pre-knowledge for the plant need not be required. Finally, the MIMO fuzzy-neural control is used to simulate a real example.
2 citations