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
••
TL;DR: A hybrid neural network method has been proposed that uses a counterpropagation neural network (CPN) in the first stage for sorting the training data into clusters, giving an approximate guess of the damage extent quickly, showing the computational superiority of the hybrid method compared with the conventional single stage method.
Abstract: A multistage identification scheme for structural damage detection using time domain acceleration responses is proposed. Previous studies of damage assessment using neural networks mostly involved training a backpropagation neural network (BPN) to learn damage patterns with significant computational effort. A hybrid neural network method has been proposed that uses a counterpropagation neural network (CPN) in the first stage for sorting the training data into clusters, giving an approximate guess of the damage extent quickly. After an approximate estimate is obtained, a new set of training patterns of reduced size is generated using the CPN prediction. In the second stage, a BPN trained with the Levenberg–Marquardt algorithm is used to learn the new training data and predict a more accurate result. A superior convergence and a substantial decrease in central processing unit time have been observed for three numerical examples. These examples show the computational superiority of the hybrid method compared...
8 citations
••
TL;DR: The proposed method which is the combination of genetic algorithm with Fuzzy ARTMAP is called GOFAM and it performs significantly better than FAM and Ordered FAM in terms of network size.
Abstract: Fuzzy ARTMAP (FAM), which is a supervised model from the adaptive resonance theory (ART) neural network family, is one of the conspicuous neural network classifier. The generalization/performance of FAM is affected by two important factors which are network parameters and presentation order of training data. In this paper we introduce a genetic algorithm to find a better presentation order of training data for FAM. The proposed method which is the combination of genetic algorithm with Fuzzy ARTMAP is called Genetic Ordered Fuzzy ARTMAP (GOFAM). To illustrate the effectiveness of GOFAM, several standard datasets from UCI repository of machine learning databases are experimented. The results are analyzed and compared with those from FAM and Ordered FAM which is used to determine a fixed order of training pattern presentation to FAM. Experimental results demonstrate the performance of GOFAM is much better than performance of Fuzzy ARTMAP and Ordered Fuzzy ARTMAP. In term of network size, GOFAM performs significantly better than FAM and Ordered FAM.
8 citations
••
TL;DR: In this paper, a hybrid neural network model is developed to predict and control the blood glucose (BG) of the patient who has type 1 diabetes mellitus (T1DM), which consists of a linear finite impulse response (FIR) model and a nonlinear autoregressive exogenous input (NARX) network.
Abstract: In this paper, a hybrid neural network model is developed to predict and control the blood glucose (BG) of the patient who has type 1 diabetes mellitus (T1DM). The proposed model consists of two parts: a linear finite impulse response (FIR) model and a nonlinear autoregressive exogenous input (NARX) network. A recently developed and well-acknowledged meal simulation model of the glucose-insulin system for T1DM is employed to create virtual subjects. Data from virtual subjects are used to identify an intermediate physiological model, and then our proposed hybrid model is trained and validated based on this intermediate model. The key features of the resulting hybrid model are that it reveals satisfactory accuracy of long-term prediction and does not require an immeasurable state for model initialization. The developed hybrid model is then embedded in a nonlinear model predictive control (MPC) controller with zone penalty weights, and this closed-loop controller is implemented on these virtual subjects for ...
8 citations
••
08 Apr 2019TL;DR: A novel hybrid neural network embedded in a deep learning framework that can be used for sentiment classification and which outperforms the alternative approaches in four sentiment classification problems.
Abstract: The ability to accurately understand opinionated content is critical for a large set of applications. Models targeting at learning from such content should overcome the inherent difficulties of the data. We propose a novel hybrid neural network embedded in a deep learning framework that can be used for sentiment classification. Our method consists of an independent set of feed forward learning models that are able to identify rich linguistic patterns through recurrent semantic trees. We evaluate our method in four sentiment classification problems that include both binary and multi-class classification tasks. Moreover, we compare our model's prediction accuracy with state-of-the-art methods. We observe that our method outperforms the alternative approaches. The strengths of the proposed approach are due to i) a novel Convolutional Neural Network which can be employed autonomously or as part of a greater framework, ii) a hybrid framework which consists of a set of independent blocks that propagates information and improve the classification task.
8 citations
••
TL;DR: This paper presents a novel and systematic approach to constructing a self-organizing and self-learning multivariable controller built on a hybrid neural network consisting of a variable-structure competitive network and a standard back-propagation neural network.
Abstract: This paper presents a novel and systematic approach to constructing a self-organizing and self-learning multivariable controller. The proposed controller is built on a hybrid neural network consisting of a variable-structure competitive network and a standard back-propagation neural network (BNN). We develop the corresponding self-organizing and learning algorithms. The controller shares certain features with traditional fuzzy controllers in terms of using error-based input forms and emphasizing the rule-based paradigms. However, knowledge representation and reasoning are here carried out by the network structure and computing, instead of logical inference. On the other hand, compared with ordinary BNN-based control paradigms the proposed controller possesses a distinctive characteristic; that is, while having the advantages of computational efficiency and trainable capability of the network paradigm, it maintains the clarity of the rule-based paradigm by self-organizing a rule-base, thereby providing an ...
8 citations