• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.71.2-71
• /
• 2001

This paper deals with nonlinear system modelling using neural network and genetic algorithm. Application of neural network to control and identification is actively studied because of their approximating ability of nonlinear function. It is important to design the neural network with optimal structure for minimum error and fast response time. Genetic algorithm is getting more popular nowadays because of their simplicity and robustness. In this paper, We optimize neural network structure using genetic algorithm. The genetic algorithm uses binary coding for neural network structure and search for optimal neural network structure of minimum error and response time. Through extensive simulation, Optimal neural network structure is shown to be effective for ...

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.12
• /
• pp.1295-1304
• /
• 2004

In this paper, the Bayesian recurrent neural network is proposed to predict time series data. A neural network predictor requests proper learning strategy to adjust the network weights, and one needs to prepare for non-linear and non-stationary evolution of network weights. The Bayesian neural network in this paper estimates not the single set of weights but the probability distributions of weights. In other words, the weights vector is set as a state vector of state space method, and its probability distributions are estimated in accordance with the particle filtering process. This approach makes it possible to obtain more exact estimation of the weights. In the aspect of network architecture, it is known that the recurrent feedback structure is superior to the feedforward structure for the problem of time series prediction. Therefore, the recurrent neural network with Bayesian inference, what we call Bayesian recurrent neural network (BRNN), is expected to show higher performance than the normal neural network. To verify the proposed method, the time series data are numerically generated and various kinds of neural network predictor are applied on it in order to be compared. As a result, feedback structure and Bayesian learning are better than feedforward structure and backpropagation learning, respectively. Consequently, it is verified that the Bayesian reccurent neural network shows better a prediction result than the common Bayesian neural network.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.649-654
• /
• 2023

This paper proposes the design of a neural network structure search model using graph convolutional neural networks. Deep learning has a problem of not being able to verify whether the designed model has a structure with optimized performance due to the nature of learning as a black box. The neural network structure search model is composed of a recurrent neural network that creates a model and a convolutional neural network that is the generated network. Conventional neural network structure search models use recurrent neural networks, but in this paper, we propose GC-NAS, which uses graph convolutional neural networks instead of recurrent neural networks to create convolutional neural network models. The proposed GC-NAS uses the Layer Extraction Block to explore depth, and the Hyper Parameter Prediction Block to explore spatial and temporal information (hyper parameters) based on depth information in parallel. Therefore, since the depth information is reflected, the search area is wider, and the purpose of the search area of the model is clear by conducting a parallel search with depth information, so it is judged to be superior in theoretical structure compared to GC-NAS. GC-NAS is expected to solve the problem of the high-dimensional time axis and the range of spatial search of recurrent neural networks in the existing neural network structure search model through the graph convolutional neural network block and graph generation algorithm. In addition, we hope that the GC-NAS proposed in this paper will serve as an opportunity for active research on the application of graph convolutional neural networks to neural network structure search.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.12
• /
• pp.804-810
• /
• 2004

There are two important things for the general purpose neural network processor. The first is a capability to build various structures of neural network, and the second is to be able to support suitable learning method for that neural network. Some way to process various learning algorithms is required for on-chip learning, because the more neural network types are to be handled, the more learning methods need to be built into. In this paper, an improved hardware structure is proposed to compute various kinds of learning algorithms flexibly. The hardware structure is based on the existing modular neural network structure. It doesn't need to add a new circuit or a new program for the learning process. It is shown that rearrangements of the existing processing elements can produce several neural network learning modules. The performance and utilization of this module are analyzed by comparing with other neural network chips.

• Journal of Navigation and Port Research
• /
• v.28 no.5
• /
• pp.435-441
• /
• 2004

This paper deals with modelling and identification of a shipboard stabilized satellite antenna system using the optimal neural network structure. It is difficult for shipboard satellite antenna system to control and identification because of their approximating ability of nonlinear function So it is important to design the neural network with optimal structure for minimum error and fast response time. In this paper, a neural network structure using genetic algorithm is optimized And genetic algorithm is also used for identifying a shipboard satellite antenna system It is noticed that the optimal neural network structure actually describes the real movement of ship well. Through practical test, the optimal neural network structure is shown to be effective for modelling the shipboard satellite antenna system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.635-639
• /
• 2004

In this paper, we present a novel approach for the structure of Fuzzy Neural Network(FNN) based on wavelet function and apply this network structure to the modeling of chaotic nonlinear systems. Generally, the wavelet fuzzy model(WFM) has the advantage of the wavelet transform by constituting the fuzzy basis function(FBF) and the conclusion part to equalize the linear combination of FBF with the linear combination of wavelet functions. However, it is very difficult to identify the fuzzy rules and to tune the membership functions of the fuzzy reasoning mechanism. Neural networks, on the other hand, utilize their learning capability for automatic identification and tuning. Therefore, we design a wavelet based FNN structure(WFNN) that merges these advantages of neural network, fuzzy model and wavelet transform. The basic idea of our wavelet based FNN is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. And our network can automatically identify the fuzzy rules by modifying the connection weights of the networks via the gradient descent scheme. To verify the efficiency of our network structure, we evaluate the modeling performance for chaotic nonlinear systems and compare it with those of the FNN and the WFM.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.1
• /
• pp.111-118
• /
• 2004

In this paper, we present a novel approach for the structure of Fuzzy Neural Network(FNN) based on wavelet function and apply this network structure to the solution of the tracking problem for mobile robots. Generally, the wavelet fuzzy model(WFM) has the advantage of the wavelet transform by constituting the fuzzy basis function(FBF) and the conclusion part to equalize the linear combination of FBF with the linear combination of wavelet functions. However, it is very difficult to identify the fuzzy rules and to tune the membership functions of the fuzzy reasoning mechanism. Neural networks, on the other hand, utilize their learning capability for automatic identification and tuning. Therefore, we design a wavelet based FNN structure(WFNN) that merges these advantages of neural network, fuzzy model and wavelet transform. The basic idea of our wavelet based FNN is to realize the process of fuzzy reasoning of wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. And our network can automatically identify the fuzzy rules by modifying the connection weights of the networks via the gradient descent scheme. To verify the efficiency of our network structure, we evaluate the tracking performance for mobile robot and compare it with those of the FNN and the WFM.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.15 no.5
• /
• pp.48-55
• /
• 2007

A bushing component of a vehicle suspension system is tested to capture the nonlinear behavior of rubber bushing element using the MTS 3-axes rubber test machine. The results of the tests are used to model the artificial neural network bushing model. The performances from the neural network model usually are dependent on the structure of the neural network. In this paper, maximum error, peak error, root mean square error, and error-to-signal ratio are employed to evaluate the performances of the neural network bushing model. A simple simulation is carried out to show the usefulness of the developed procedure.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1565-1568
• /
• 2003

In this paper, we propose modular network to solve difficult and complex problems that are seldom solved with multi-layer neural network. The structure of modular neural network in researched by Jacobs and Jordan is selected in this paper. Modular network consists of several expert networks and a gating network which is composed of single-layer neural network or multi-layer neural network. We propose modular network structure using recurrent neural network, since the state of the whole network at a particular time depends on an aggregate of previous states as well as on the current input. Finally, we show excellence of the proposed network compared with modular network.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.195-198
• /
• 2000

We propose a new wavelet neural network structure, for which we apply new recurrent nodes to the network, in this paper for the dynamic system identification and control. We will construct the wavelet neural network by using wavelet frame function. The function does not have the best approximation property, but it may be possible to apply some modification to the structure of the network because the constriction of orthogonality is loosened a little. This wavelet neural network we propose can obtain previous state information by its structure of the network without any addition of input, though the conventional wavelet network needs additional previous state input for the improvement of the dynamic performance. In numerical experience, the performance of the new wavelet neural network we propose in the nonlinear system with uncertainity of parameter Is equal to that of the wavelet network which used the additional previous information input, superior to that of the conventional wavelet network.