scispace - formally typeset
Search or ask a question
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
More filters
01 Jan 2011
TL;DR: The comparison of performance of GA-LM with the conventional Back -Propagation(BP)algorithm revealed that the predicted DO values using GA- LM model are in good agreement with the measured data, indicating that the model is capable of predicting DO accurately and rapidly.
Abstract: The prediction of dissolved oxygen(DO)level is complicated in aquaculture ponds as a complex system with multi-variables,nonlinearity and long-time lag.In this study,GA-LM,a hybrid neural network model combining Levenberg Marquardt(LM)algorithm and Genetic Algorithm(GA)was developed for DO level predicting in an aquaculture pond at Dalian,China.The The comparison of performance of GA-LM with the conventional Back -Propagation(BP)algorithm revealed that the predicted DO values using GA-LM model are in good agreement with the measured data,indicating that the model is capable of predicting DO accurately and rapidly.

2 citations

Proceedings ArticleDOI
25 Oct 1993
TL;DR: The proposed model is effective for the acoustic diagnosis of a compressor using a hybrid neural network using a Gaussian potential function network and a backpropagation network, and 93.6% discrimination accuracy is obtained in this experiment.
Abstract: Describes the acoustic diagnosis technique for a compressor using a hybrid neural network (HNN). The HNN is composed of two neural networks, an acoustic feature extraction network using a backpropagation network (BPN) and a fault discrimination network using a Gaussian potential function network (GPFN). The BPN is composed of five layers and the number of the middle hidden units is smaller than the others. The target patterns for the output layer are the same as the input patterns. After the learning of the network, the middle hidden layer acquires the compressed input information. The input patterns of the GPFN are the output values of the middle hidden layer in the BPN. The task of the HNN is to discriminate four conditions of the valve under various experimental conditions. As a result, 93.6% discrimination accuracy is obtained in this experiment. This suggests that the proposed model is effective for the acoustic diagnosis.

2 citations

Posted Content
TL;DR: A neural network architecture (HydroDeep) that couples a process-based hydro-ecological model with a combination of Deep Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) Network to build a hybrid baseline model.
Abstract: Due to limited evidence and complex causes of regional climate change, the confidence in predicting fluvial floods remains low. Understanding the fundamental mechanisms intrinsic to geo-spatiotemporal information is crucial to improve the prediction accuracy. This paper demonstrates a hybrid neural network architecture - HydroDeep, that couples a process-based hydro-ecological model with a combination of Deep Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) Network. HydroDeep outperforms the independent CNN's and LSTM's performance by 1.6% and 10.5% respectively in Nash-Sutcliffe efficiency. Also, we show that HydroDeep pre-trained in one region is adept at passing on its knowledge to distant places via unique transfer learning approaches that minimize HydroDeep's training duration for a new region by learning its regional geo-spatiotemporal features in a reduced number of iterations.

2 citations

Proceedings ArticleDOI
01 Nov 2005
TL;DR: A hybrid technique for speech recognition which applying 2 different neural network architecture, self-organizing map (SOM) and multilayer perceptron (MLP) for Malay syllables speech recognition.
Abstract: We proposed a hybrid technique for speech recognition which applying 2 different neural network architecture. The proposed technique combines self-organizing map (SOM) which known as unsupervised network and multilayer perceptron (MLP) which known as supervised network for Malay syllables speech recognition. We used a 2D self-organizing feature map as a feature extractor which acts as a sequential mapping function in order to transform the acoustic vector sequences of speech signal into trajectories. The output of SOM is a matrix with same dimension and its elements take on binary values. The transformation of the feature vector simplifies the classification task by recognizer using multilayer perceptron. The MLP classifies the binary trajectories that each syllable corresponds to. Experiments were conducted on the 15 Malay syllables by 10 speakers for conventional technique (MLP only) and proposed technique (SOM and MLP). Our technique has achieved better performance where improves the accuracy up to 4.5%.

2 citations

Book ChapterDOI
20 Oct 2013
TL;DR: This paper proposes a hybrid neural network model combining the MTRNN with a deep learning neural network DN, which is to overcome the problem related to the initial state setting in the M TRNN, and applies this approach to 20 motion skeleton units obtained by KINECT.
Abstract: Multiple timescale recurrent neural network MTRNN model is a useful tool to model a continuous signal for a dynamic task such as human action recognition. Different setting of initial states in the MTRNN brings us convenience to predict multiple signals using the same network model. On the contrary, optimal switching for suitable initial states in the slow context unit of the MTRNN becomes critical condition to achieve desired multiple dynamic tasks. In this paper, we propose a hybrid neural network model combining the MTRNN with a deep learning neural network DN, which is to overcome the problem related to the initial state setting in the MTRNN. The DN together with MTRNN generates a suitable initial state for the slow context units in the MTRNN according to automatically detected situation change. We apply our approach to 20 motion skeleton units, which is obtained by KINECT, to construct three kinds of human motion sequences. The results show that the proposed method is able to recognize various motions using proper initial state information in a real-time procedure.

2 citations


Network Information
Related Topics (5)
Artificial neural network
207K papers, 4.5M citations
89% related
Feature extraction
111.8K papers, 2.1M citations
88% related
Fuzzy logic
151.2K papers, 2.3M citations
85% related
Convolutional neural network
74.7K papers, 2M citations
84% related
Deep learning
79.8K papers, 2.1M citations
83% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
20233
20228
2021128
2020119
2019104
201863