• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10b
• /
• pp.1256-1258
• /
• 1990

A large number of trainings are requested for the artificial neural network using the backpropagation algorithm. It is shown that one dimensional search technique is effective to reduce the number of trainings through some numerical simulations.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.5
• /
• pp.1466-1474
• /
• 2016

• Structural Engineering and Mechanics
• /
• v.37 no.6
• /
• pp.575-592
• /
• 2011

For seismic resistant design of critical structures, a dynamic analysis, either response spectrum or time history is frequently required. Owing to the lack of recorded data and the randomness of earthquake ground motion that may be experienced by structure in the future, usually it is difficult to obtain recorded data which fit the requirements (site type, epicenteral distance, etc.) well. Therefore, the artificial seismic records are widely used in seismic designs, verification of seismic capacity and seismic assessment of structures. The purpose of this paper is to develop a numerical method using Artificial Neural Network (ANN) and wavelet packet transform in best basis method which is presented for the decomposition of artificial earthquake records consistent with any arbitrarily specified target response spectra requirements. The ground motion has been modeled as a non-stationary process using wavelet packet. This study shows that the procedure using ANN-based models and wavelet packets in best-basis method are applicable to generate artificial earthquakes compatible with any response spectra. Several numerical examples are given to verify the developed model.

• ETRI Journal
• /
• v.45 no.2
• /
• pp.318-328
• /
• 2023

Recently, embedded systems, such as mobile platforms, have multiple processing units that can operate in parallel, such as centralized processing units (CPUs) and neural processing units (NPUs). We can use deep-learning compilers to generate machine code optimized for these embedded systems from a deep neural network (DNN). However, the deep-learning compilers proposed so far generate codes that sequentially execute DNN operators on a single processing unit or parallel codes for graphic processing units (GPUs). In this study, we propose PartitionTuner, an operator scheduler for deep-learning compilers that supports multiple heterogeneous PUs including CPUs and NPUs. PartitionTuner can generate an operator-scheduling plan that uses all available PUs simultaneously to minimize overall DNN inference time. Operator scheduling is based on the analysis of DNN architecture and the performance profiles of individual and group operators measured on heterogeneous processing units. By the experiments for seven DNNs, PartitionTuner generates scheduling plans that perform 5.03% better than a static type-based operator-scheduling technique for SqueezeNet. In addition, PartitionTuner outperforms recent profiling-based operator-scheduling techniques for ResNet50, ResNet18, and SqueezeNet by 7.18%, 5.36%, and 2.73%, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.11-20
• /
• 2006

This paper describes the technique which utilizes a fuzzy neural network to sketch feature extraction in digital images. We configure an artificial neural network and make it learn fuzzy membership functions to decide a local threshold applying to sketch feature extraction. To do this. we put the learning data which is membership functions generated based on optimal feature map of a few standard images into the artificial neural network. The proposed technique extracts sketch features in an images very effectively and rapidly because the input fuzzy variable have some desirable characteristics for feature extraction such as dependency of local intensity and excellent performance and the proposed fuzzy neural network is learned from their membership functions, We show that the fuzzy neural network has a good performance in extracting sketch features without human intervention.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.613-618
• /
• 2022

Research on artificial intelligence based on SNN (Spiking Neural Networks) is drawing attention as a next-generation artificial intelligence that can overcome the limitations of artificial intelligence based on DNN (Deep Neural Networks) that is currently popular. In this paper, we describe the structure of the SNN compiler, a system SW that generate code from SNN description for neuromorphic computing systems. We also introduce the algorithms used for compiler implementation and present experimental results on how the execution time varies in neuromorphic computing systems depending on the the mapping algorithm. The mapping algorithm proposed in the text showed a performance improvement of up to 3.96 times over a random mapping. The results of this study will allow SNNs to be applied in various neuromorphic hardware.

• Design & Manufacturing
• /
• v.17 no.4
• /
• pp.72-78
• /
• 2023

Injection molding is a process widely used in various industries because of its high production speed and ease of mass production during the plastic manufacturing process, and the product is molded by injecting molten plastic into the mold at high speed and pressure. Since process conditions such as resin and mold temperature mutually affect the process and the quality of the molded product, it is difficult to accurately predict quality through mathematical or statistical methods. Recently, studies to predict the quality of injection molded products by applying artificial neural networks, which are known to be very useful for analyzing nonlinear types of problems, are actively underway. In this study, structural optimization of neural networks was conducted by applying multi-task learning techniques according to the characteristics of the input and output parameters of the artificial neural network. A structure reflecting the characteristics of each process step was applied to the input parameters, and a structure reflecting the quality characteristics of the injection molded part was applied to the output parameters using multi-tasking learning. Building an artificial neural network to predict the three qualities (mass, diameter, height) of injection-molded product under six process conditions (melt temperature, mold temperature, injection speed, packing pressure, pacing time, cooling time) and comparing its performance with the existing neural network, we observed enhancements in prediction accuracy for mass, diameter, and height by approximately 69.38%, 24.87%, and 39.87%, respectively.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.04a
• /
• pp.235-241
• /
• 2000

This article suggests integrated neural network models for the interest rate forecasting using change point detection. The basic concept of proposed model is to obtain intervals divided by change point, to identify them as change-point groups, and to involve them in interest rate forecasting. the proposed models consist of three stages. The first stage is to detect successive change points in interest rate dataset. The second stage is to forecast change-point group with data mining classifiers. The final stage is to forecast the desired output with BPN. Based on this structure, we propose three integrated neural network models in terms of data mining classifier: (1) multivariate discriminant analysis (MDA)-supported neural network model, (2) case based reasoning (CBR)-supported neural network model and (3) backpropagation neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural network model alone and, in addition, determine which of three classifiers (MDA, CBR and BPN) can perform better. This article is then to examine the predictability of integrated neural network models for interest rate forecasting using change-point detection.

• Proceedings of the Korean Society for Quality Management Conference
• /
• 1998.11a
• /
• pp.696-704
• /
• 1998

Artificial neural networks (ANN) have successfully applied into various areas. But, How to effectively established network is the one of the critical problem. This study will focus on this problem and try to extensively study. Firstly, four different learning algorithms ANNs were constructed. The learning algorithms include backpropagation, simulated annealing, genetic algorithm, and tabu search. The experimental results of the above four different learning algorithms were tested by statistical analysis. The training RMS, training time, and testing RMS were used as the comparison criteria.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.3
• /
• pp.281-287
• /
• 1999

In this paper, a design method based on evolutionary programming for feedforward neural networks which have a single hidden layer is presented. By using an evolutionary programming, the network parameters such as the network structure, weight, slope of sigmoid functions and bias of nodes can be acquired simultaneously. To check the effectiveness of the suggested method, two numerical examples are examined. The performance of the identified network is demonstrated.