• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 A
• /
• pp.171-174
• /
• 2003

In this paper, a Learning module for a reconfigurable neural network processor(ERNIE) was proposed for an On-chip learning. The existing reconfigurable neural network processor(ERNIE) has a much better performance than the software program but it doesn't support On-chip learning function. A learning module which is based on Back Propagation algorithm was designed for a help of this weak point. A pipeline structure let the learning module be able to update the weights rapidly and continuously. It was tested with five types of alphabet font to evaluate learning module. It compared with C programed neural network model on PC in calculation speed and correctness of recognition. As a result of this experiment, it can be found that the neural network processor(ERNIE) with learning module decrease the neural network training time efficiently at the same recognition rate compared with software computing based neural network model. This On-chip learning module showed that the reconfigurable neural network processor(ERNIE) could be a evolvable neural network processor which can fine the optimal configuration of network by itself.

• 전자공학회논문지B
• /
• 제32B권1호
• /
• pp.120-126
• /
• 1995

The diffusion neural network can be cfficiently applied to the Gaussian processing. For example, a difference of two Gaussians(DOG) is performed by this network with ease. In this paper, we model a neural network to perform the function /t(.del.${\Delta}^{2}$G) by using the diffusion neural network. This model is used to detect the edges of moving target in image. By this model not only moving target is separated from stationary background but also their trajectories are obtained using accumulated past information in the diffusion neural network. Furthermore this model needs a small number of connections per cell and the connection weights are fixed-valued. Therefore its hardware can be easily implemented with simple structure.

• 한국자동차공학회논문집
• /
• 제12권4호
• /
• pp.110-118
• /
• 2004

In this paper, a blackbox approach is carried out to model the nonlinear dynamic bushing model. One-axis durability test is performed to describe the mechanical behavior of typical vehicle elastomeric components. The results of the tests are used to develop an empirical bushing model with an artificial neural network. The back propagation algorithm is used to obtain the weighting factor of the neural network. Since the output for a dynamic system depends on the histories of inputs and outputs, Narendra's algorithm of ‘NARMAX’ form is employed in the neural network bushing module. A numerical example is carried out to verify the developed bushing model.

• 한국지능시스템학회논문지
• /
• 제11권8호
• /
• pp.701-708
• /
• 2001

최근 컴퓨터의 지능에 대한 연구가 활발히 진행되고 있으며, 불확실하고 복잡한 동적 환경에서도 적응할 수 있도록 그 영역을 확장해 가고 있다. 본 논문에서는 다치논리를 기반으로 한 다치오토마타 모델을 신경망으로 구현한 다치-신경망 시스템을 제안한다. 또한, 다치오토마타는 신경망으로 구현될 수 있고, 다치-신경망 모델은 다치오토마타로 시뮬레이션될 수 있음을 입증하였다. 그 결과, 다치-신경망 모델은 지능시스템, 뇌의 모델링과 같은 여러 응용 분야에 널리 사용될 수 있을 것으로 기대된다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2006년도 추계학술대회 논문집
• /
• pp.1405-1410
• /
• 2006

Purpose of this research is that offers basic data for optimized design using neural network method to calculate consolidation settlement in study area. In this research, preformed the neural network method that analyzed the settlement characteristics of soft ground nearby study area. Thus, data base established on ground properties and consolidation settlement of neighboring area. In addition, designed the optimum neural network model for prediction of settlement through network learning and consolidation settlement prediction using consolidation settlement DB and ground properties DB. Optimized neural network model decided by repeated learning for various case of hidden layers. In this study, proposed that the optimized consolidation settlement calculation method using neural network and verified which is the optimized consolidation settlement calculation method using neural network.

• 응용통계연구
• /
• 제37권2호
• /
• pp.139-155
• /
• 2024

본 연구는 좌측 해마 경화를 보인 내측두엽 뇌전증(left mTLE, mesial temporal lobe epilepsy with left hippocampal sclerosis) 환자군과 우측 해마 경화를 보인 내측두엽 뇌전증(right mTLE, mesial temporal lobe epilepsy with right hippocampal sclerosis) 환자군 그리고 건강한 대조군(healthy controls; HC)으로부터 측정한 뇌자도(magnetoencephalography; MEG) 데이터로 각 그룹을 분류하는 다중 분류 작업에 다양한 인공신경망을 적용하고 그 결과를 비교해 보고자 하였다. 합성곱 신경망, 순환 신경망 그리고 그래프 신경망으로 모델링한 결과, k-fold 정확도 평균은 합성곱 신경망 기반 모델, 그래프 신경망 기반 모델, 순환 신경망 기반 모델 순으로 우수하였다. 또한, 수행 시간은 순환 신경망 기반 모델, 그래프 신경망 기반 모델, 합성곱 신경망 기반 모델 순으로 우수하였다. 정확도 성능과 시간 면에서 모두 좋은 수치를 보이며, 네트워크 데이터의 확장성이 뛰어난 그래프 신경망이 앞으로 뇌 연구에 활용되기 적합한 모델임을 강조하고자 한다.

• 전기전자학회논문지
• /
• 제20권3호
• /
• pp.303-306
• /
• 2016

본 논문에서는 GPGPU를 활용하여 Convolutional neural network의 가속화 방법을 제안한다. Convolutional neural network는 이미지의 특징 값을 학습하여 분류하는 neural network의 일종으로 대량의 데이터를 학습해야하는 영상 처리에 적합하다. 기존의 Convolutional neural network의 convolution layer는 다수의 곱셈 연산을 필요로 하여 임베디드 환경에서 실시간으로 동작하기에 어려움이 있다. 본 논문에서는 이러한 단점을 해결하기 위하여 winograd convolution 연산을 통하여 곱셈 연산을 줄이고 GPGPU의 SIMT 구조를 활용하여 convolution 연산을 병렬 처리한다. 실험은 ModelSim, TestDrive를 사용하여 진행하였고 실험 결과 기존의 convolution 연산보다 처리 시간이 약 17% 개선되었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.243-247
• /
• 1992

This paper describes a neural network based control scheme with MRAC. The system consists of two neural network; one is for identifier and the other is for controller. Identification is firstly performed to learn the behavior of the nonlinear plant. Neural net controller is next trained by backpropagating the error at the output of plant through the identifier. Also the training method used in this paper repeatedly updates weights of neural network to track the reference model.

• 한국컴퓨터정보학회논문지
• /
• 제22권4호
• /
• pp.41-49
• /
• 2017

Word sense disambiguation(WSD) that determines the exact meaning of homonym which can be used in different meanings even in one form is very important to understand the semantical meaning of text document. Many recent researches on WSD have widely used NNLM(Neural Network Language Model) in which neural network is used to represent a document into vectors and to analyze its semantics. Among the previous WSD researches using NNLM, RNN(Recurrent Neural Network) model has better performance than other models because RNN model can reflect the occurrence order of words in addition to the word appearance information in a document. However, since RNN model uses only the forward order of word occurrences in a document, it is not able to reflect natural language's characteristics that later words can affect the meanings of the preceding words. In this paper, we propose a WSD scheme using Bidirectional RNN that can reflect not only the forward order but also the backward order of word occurrences in a document. From the experiments, the accuracy of the proposed model is higher than that of previous method using RNN. Hence, it is confirmed that bidirectional order information of word occurrences is useful for WSD in Korean language.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.165-172
• /
• 2019

Machine-learning techniques have been actively employed to information security in recent years. Traditional rule-based security solutions are vulnerable to advanced attacks due to unpredictable behaviors and unknown vulnerabilities. By employing ML techniques, we are able to develop intrusion detection systems (IDS) based on anomaly detection instead of misuse detection. Moreover, threshold issues in anomaly detection can also be resolved through machine-learning. There are very few datasets for network intrusion detection compared to datasets for malicious code. KDD CUP 99 (KDD) is the most widely used dataset for the evaluation of IDS. Numerous studies on ML-based IDS have been using KDD or the upgraded versions of KDD. In this work, we develop an IDS model using CSE-CIC-IDS 2018, a dataset containing the most up-to-date common network attacks. We employ deep-learning techniques and develop a convolutional neural network (CNN) model for CSE-CIC-IDS 2018. We then evaluate its performance comparing with a recurrent neural network (RNN) model. Our experimental results show that the performance of our CNN model is higher than that of the RNN model when applied to CSE-CIC-IDS 2018 dataset. Furthermore, we suggest a way of improving the performance of our model.