• 한국지능시스템학회논문지
• /
• 제17권4호
• /
• pp.472-476
• /
• 2007

학습법칙은 신경회로망의 성능에 중요한 영향을 미친다. 본 논문은 데이터와 클래스들의 대표값들 사이의 거리를 고려하여 학습률을 정하는 새로운 퍼지 학습법칙을 제안한다. 클래스들의 대표값을 조정할 때, 이러한 고려는 outlier에 비하여 결정경계선 근처에 있는 데이터의 반영도를 높임으로써 outlier의 클래스의 대표값에 미치는 영향도를 낮출 수 있다. 따라서 outlier들이 결정경계선을 악화시키는 것을 방지할 수 있다. 이 새로운 퍼지 학습법칙을 IAFC(Integrated Adaptive Fuzzy Clustering) 신경회로망에 적용하였다. 제안한 퍼지 신경회로망과 다른 감독 신경회로망들의 성능을 비교하기 위하여 iris 데이터를 사용하였다. iris 데이터를 사용하여 테스트한 결과 제안한 퍼지 신경회로망의 성능이 우수함을 보였다.

• 한국정보교육학회:학술대회논문집
• /
• 한국정보교육학회 2021년도 학술논문집
• /
• pp.385-391
• /
• 2021

본 논문에서는 예비교사 및 현직교사를 대상으로 한 인공지능 소양교육을 위해, 딥러닝 인공신경망 교육 사례를 연구하였다. 또한, 제안한 교육 사례를 통해, 초중고 학생들이 경험할 수 있는 인공신경망 원리교육 콘텐츠를 탐색하고자 하였다. 이를 위해, 우선 2종 이미지를 인식하는 인공신경망의 동작 원리 교육 사례를 제시하였다. 그리고 인공신경망 확장 응용 교육 사례로, 3종 이미지를 인식하는 인공신경망 교육 사례를 제시하였다. 인공신경망에 인식시키고자 하는 이미지 개수에 따라 출력층의 개수를 변경하여 스프레드시트로 구현한 사례를 구분하여 설명하였다. 또한, 인공신경망 동작 결과를 체험하기 위해, 지도학습 방식의 인공신경망에 필요한 학습데이터를 직접 작성해보는 교육 내용을 제시하였다. 본 논문에서는 인공신경망의 구현과 인식 테스트 결과를 스프레드시트를 사용하여 시각적으로 나타내었다.

• 정보학연구
• /
• 제8권1호
• /
• pp.119-124
• /
• 2005

Learning procedure in the neural network is updating of weights between neurons. Unadequate initial learning coefficient causes excessive iterations of learning process or incorrect learning results and degrades learning efficiency. In this paper, adaptive learning algorithm is proposed to increase the efficient in the learning algorithms of Kohonens Self-Organization Neural networks. The algorithm updates the weights adaptively when learning procedure runs. To prove the efficiency the algorithm is experimented to clustering of the random weight. The result shows improved learning rate about 42~55% ; less iteration counts with correct answer.

• 전자공학회논문지B
• /
• 제30B권1호
• /
• pp.79-89
• /
• 1993

This paper deals with a computer aided control of an adjustment process for the complete electronic devices by means of an application of artificial neural network and an implementation of neuro-controller for intelligent control. Multi-layer neural network model is employed as artificial neural network with the learning method of the error back propagation. Information initially available from real plant under control are the initial values of plant output, and the augmented plant input and its corresponding plant output at that time. For the intelligent control of adjustment process utilizing artificial neural network, the neural network emulator (NNE) and the neural network controller(NNC) are developed. The initial weights of each neural network are determined through off line learning for the given product and it is also employed to cope with environments of the another product by on line learning. Computer simulation, as well as the application to the real situation of proposed intelligent control system is investigated.

• 정보기술과데이타베이스저널
• /
• 제3권2호
• /
• pp.75-96
• /
• 1996

This study is intended to compare the effectiveness of the neural network inductive learning model with a vector space model in information retrieval. As a result, searches responding to incomplete queries in the neural network inductive learning model produced a higher precision and recall as compared with searches responding to complete queries in the vector space model. The results show that the hybrid methodology of integrating an inductive learning technique with the neural network model can help solve information retrieval problems that are the results of inconsistent indexing and incomplete queries--problems that have plagued information retrieval effectiveness.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.411-425
• /
• 2021

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4246-4267
• /
• 2020

As the network goes deep into all aspects of people's lives, the number and the complexity of network traffic is increasing, and traffic classification becomes more and more important. How to classify them effectively is an important prerequisite for network management and planning, and ensuring network security. With the continuous development of deep learning, more and more traffic classification begins to use it as the main method, which achieves better results than traditional classification methods. In this paper, we provide a comprehensive review of network traffic classification based on deep learning. Firstly, we introduce the research background and progress of network traffic classification. Then, we summarize and compare traffic classification based on deep learning such as stack autoencoder, one-dimensional convolution neural network, two-dimensional convolution neural network, three-dimensional convolution neural network, long short-term memory network and Deep Belief Networks. In addition, we compare traffic classification based on deep learning with other methods such as based on port number, deep packets detection and machine learning. Finally, the future research directions of network traffic classification based on deep learning are prospected.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.27-34
• /
• 1996

GENIE is a learning-based engine for building intelligent systems. Learning in GENIE proceeds by incrementally modeling its human or technical environment using a neural network and a genetic algorithm. The neural network is used to represent the knowledge for solving a given task and has the ability to grow its structure. The genetic algorithm provides the neural network with training examples by actively exploring the example space of the problem. Integrated into the training examples by actively exploring the example space of the problem. Integrated into the GENIE system architecture, the genetic algorithm and the neural network build a virtually self-teaching autonomous learning system. This paper describes the structure of GENIE and its learning components. The performance is demonstrated on a robot learning problem. We also discuss the lessons learned from experiments with GENIE and point out further possibilities of effectively hybridizing genetic algorithms with neural networks and other softcomputing techniques.

• 디지털산업정보학회논문지
• /
• 제19권4호
• /
• pp.127-136
• /
• 2023

Many research results on the traffic enforcement of illegal driving of twowheeled motor vehicles using license plate recognition are introduced. Deep learning convolutional neural networks can be used for character and word recognition of license plates because of better generalization capability compared to traditional Backpropagation neural networks. In the plates of twowheeled motor vehicles, the interdependent government and city words are included. If we implement the mutually independent word recognizers using error correction rules for two word recognition results, efficient license plate recognition results can be derived. The CPU based convolutional neural network without library under real time processing has an advantage of low cost real application compared to GPU based convolutional neural network with library. In this paper twowheeled motor vehicle license plate recognition algorithm is introduced using CPU based deep-learning convolutional neural network. The experimental results show that the proposed plate recognizer has 96.2% success rate for outdoor twowheeled motor vehicle images in real time.

• 한국지능시스템학회논문지
• /
• 제16권4호
• /
• pp.460-465
• /
• 2006

본 논문은 입력 벡터와 클래스들의 대표값들간의 유클리디안 거리들을 사용한 새로운 퍼지 학습법칙을 제안한다. 이 새로운 퍼지 학습을 supervised IAFC(Integrated Adaptive Fuzzy Clustering) 신경회로망 4에 적용하였다. 이 신경회로망은 안정성을 유지하면서도 유연성을 가지고 있다. iris 데이터를 사용하여 테스트한 결과 supervised IAFC 신경회로망 4는 오류역전파 신경회로망과 LVQ 알고리듬보다 성능이 우수하였다.