• 대한전기학회논문지
• /
• 제45권3호
• /
• pp.444-450
• /
• 1996

A digital hardware architecture for artificial neural network with learning capability is described in this paper. It is a modified hardware architecture known as HANNIBAL(Hardware Architecture for Neural Networks Implementing Back propagation Algorithm Learning). For implementing an efficient neural network hardware, we analyzed various type of multiplier which is major function block of neuro-processor cell. With this result, we design a efficient digital neural network hardware using serial/parallel multiplier, and test the operation. We also analyze the hardware efficiency with logic level simulation. (author). refs., figs., tabs.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1996년도 International Conference on Agricultural Machinery Engineering Proceedings
• /
• pp.325-333
• /
• 1996

This study was conducted to develop neural networks of predicting the sugar content of fruits based on the optical densities obtained from a spectrophotometer. Pear, apple and peach were used in investigating the feasbility of the developed neural networks as a nondestructive measurement. A spectrophotometer was used to measure the optical densities of test fruits. The neural networks suggested in this study consisted of multi-layers having one hidden layer and one output layer. The correlation coefficients between the predicted and the measured sugar content for most fruits were high. The neural networks using 2nd derivatives of optical density spectrum produced a better results in predicting the sugar content of fruits. This study contributed to develop a method for nondestructively predicting the sugar content of fruits.

• 한국시뮬레이션학회논문지
• /
• 제14권4호
• /
• pp.55-68
• /
• 2005

The advancement in semiconductor technology is leading toward smaller critical dimension designs and larger wafer manufactures. Due to such phenomena, semiconductor industry is in need of an accurate control of the process. Photolithography is one of the key processes where the pattern of each layer is formed. In this process, precise superposition of the current layer to the previous layer is critical. Therefore overlay parameters of the semiconductor photolithography process is targeted for this research. The complex relationship among the input parameters and the output metrologies is difficult to understand and harder yet to model. Because of the superiority in modeling multi-nonlinear relationships, neural networks is used for the simulator modeling. For training the neural networks, conjugate gradient method is employed. An experiment is performed to evaluate the performance among the proposed neural network simulator, stepwise regression model, and the currently practiced prediction model from the test site.

• International journal of advanced smart convergence
• /
• 제9권3호
• /
• pp.85-96
• /
• 2020

It is important to extract salient object image and to solve the invariance problem for image recognition. In this paper we propose a new hybrid algorithm for invariance and improved classification performance in image recognition, whose algorithm is combined by FT(Frequency-tuned Salient Region Detection) algorithm, Guided filter, Zernike moments, and a simple artificial neural network (Multi-layer Perceptron). The conventional FT algorithm is used to extract initial salient object image, the guided filtering to preserve edge details, Zernike moments to solve invariance problem, and a classification to recognize the extracted image. For guided filtering, guided filter is used, and Multi-layer Perceptron which is a simple artificial neural networks is introduced for classification. Experimental results show that this algorithm can achieve a superior performance in the process of extracting salient object image and invariant moment feature. And the results show that the algorithm can also classifies the extracted object image with improved recognition rate.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.88.4-88
• /
• 2001

In this paper, we propose a solver for differential equations, using a multi-layer neural network. The multi-layer neural network is a transformer function originally where the function is differential and the explicit representation has been developed. The learning determines the response of neural networks; however, the response is not equal to the output values. The differential relations are also the response. The differential conditions can be also set as teaching data; therefore, there is a possibility to reach a new solver for the differential equations. Since it is unknown how to define the input data for the neural network solver during long terms, we could not derive the expressions. Recently, the analogue type neural network is known and it transforms any vector to another The "any" must be...

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.147-150
• /
• 1996

This paper describes controller design and implementation method for controlling the temperature distribution in a thermal stratified wind tunnel(TSWT) by using a neural network algorithm. It is impossible to derive a mathematical model of the relation between heat inputs and temperature outputs in the test section of the TSWT governed by a nonlinear turbulent flow. Thus inverse neural network models with a multi layer perceptron structure are used in a feedforward control loop and feedback control loop to generate an arbitrary temperature distribution in the test section of the TSWT.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.482-485
• /
• 1999

In this paper we proposed a heterogeneous hidden layer consisting of both sigmoid functions and RBFs(Radial Basis Function) in multi-layered neural networks. Focusing on the orthogonal relationship between the sigmoid function and its derivative, a derived RBF that is a derivative of the sigmoid function is used as the RBF in the neural network. so the proposed neural network is called ONN(Orthogonal Neural Network). Identification results using a nonlinear function confirm both the ONN＇s feasibility and characteristics by comparing with those obtained using a conventional neural network which has sigmoid function or RBF in hidden layer

• International journal of advanced smart convergence
• /
• 제9권2호
• /
• pp.173-178
• /
• 2020

A common problem with neural network learning is that it is too suitable for the specificity of learning. In this paper, various methods were compared to avoid overfitting: regularization, drop-out, different numbers of data and different types of neural networks. Comparative studies of the above-mentioned methods have been provided to evaluate the test accuracy. I found that the more data using method is better than the regularization and dropout methods. Moreover, we know that deep convolutional neural networks outperform multi-layer neural networks and simple convolution neural networks.

• 반도체디스플레이기술학회지
• /
• 제15권3호
• /
• pp.18-23
• /
• 2016

QFN (Quad Flat No-leads Package) is one of the SMD (Surface Mount Device). Since there is no lead in QFN, there are many defects on solder. Therefore, we propose an efficient mechanism for QFN solder defect detection at this paper. For this, we employ Convolutional Neural Network (CNN) of the Machine Learning algorithm. QFN solder's color multi-layer images are used to train CNN. Since these images are 3-channel color images, they have a problem with applying to CNN. To solve this problem, we used each 1-channel grayscale image (Red, Green, Blue) that was separated from 3-channel color images. We were able to detect QFN solder defects by using this CNN. In this paper, it is shown that the CNN is superior to the conventional multi-layer neural networks in detecting QFN solder defects. Later, further research is needed to detect other QFN.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권4호
• /
• pp.327-332
• /
• 2005

We investigatea new fuzzy-neural networks-Hybrid Fuzzy set based polynomial Neural Networks (HFSPNN). These networks consist of genetically optimized multi-layer with two kinds of heterogeneous neurons thatare fuzzy set based polynomial neurons (FSPNs) and polynomial neurons (PNs). We have developed a comprehensive design methodology to determine the optimal structure of networks dynamically. The augmented genetically optimized HFSPNN (namely gHFSPNN) results in a structurally optimized structure and comes with a higher level of flexibility in comparison to the one we encounter in the conventional HFPNN. The GA-based design procedure being applied at each layer of gHFSPNN leads to the selection leads to the selection of preferred nodes (FSPNs or PNs) available within the HFSPNN. In the sequel, the structural optimization is realized via GAs, whereas the ensuing detailed parametric optimization is carried out in the setting of a standard least square method-based learning. The performance of the gHFSPNN is quantified through experimentation where we use a number of modeling benchmarks synthetic and experimental data already experimented with in fuzzy or neurofuzzy modeling.