• The Transactions of the Korean Institute of Electrical Engineers A
• /
• 제48권4호
• /
• pp.419-427
• /
• 1999

We propose an algorithm for obtaining the optimal node number of hidden units in dynamic neural networks. The dynamic nerual networks comprise of dynamic neural units and neural processor consisting of two dynamic neural units; one functioning as an excitatory neuron and the other as an inhibitory neuron. Starting out with basic network structure to solve the problem of control, we find optimal neural structure by multiplication and combining dynamic neural unit. Numerical examples are presented for nonlinear systems. Those case studies showed that the proposed is useful is practical sense.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• 제53권3호
• /
• pp.134-141
• /
• 2004

Recently, neural network techniques are widely used in adaptive and learning control schemes for production systems. However, in general it takes up a lot of time to learn in the case applied in control system. Furthermore, the physical meaning of neural networks constructed as a result is not obvious. And in practice since it is difficult for the PID gains suitably, lots of researches have been reported with respect of turning schemes of PID gains. A neural network-based PID control scheme is proposed, which extracts skills of human experts as PID gains. This controller is designed by using three-layered neural networks. The effectiveness of the proposed neural network-based PID control scheme is investigated through an application for a production control system. This control method can enable a plant to operate smoothy and obviously as the plant condition varies with any unexpected accidents.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 B
• /
• pp.717-719
• /
• 2003

Recently Neural Network techniques have widely used in adaptive and learning control schemes for production systems. However, generally it costs a lot of time for learning in the case applied in control system. Furthermore, the physical meaning of neural networks constructed as a result is not obvious. And in practice since it is difficult to the PID gains suitably lots of researches have been reported with respect to turning schemes of PID gains. A Neural Network-based PID control scheme is proposed, which extracts skills of human experts as PID gains. This controller is designed by using three-layered neural networks. The effectiveness of the proposed Neural Network-based PID control scheme is investigated through an application for a production control system. This control method can enable a plant to operate smoothy and obviously as the plant condition varies with any unexpected accident.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2018년도 춘계학술발표대회
• /
• pp.377-380
• /
• 2018

인간의 추론 능력이란 문제에 주어진 조건을 보고 문제 해결에 필요한 것이 무엇인지를 논리적으로 생각해 보는 것으로 문제 상황 속에서 일정한 규칙이나 성질을 발견하고 이를 수학적인 방법으로 법칙을 찾아내거나 해결하는 능력을 말한다. 이러한 인간인지 능력과 유사한 인공지능 시스템을 개발하는데 있어서 핵심적 도전은 비구조적 데이터(unstructured data)로부터 그 개체들(object)과 그들간의 관계(relation)에 대해 추론하는 능력을 부여하는 것이라고 할 수 있다. 지금까지 딥러닝(deep learning) 방법은 구조화 되지 않은 데이터로부터 문제를 해결하는 엄청난 진보를 가져왔지만, 명시적으로 개체간의 관계를 고려하지 않고 이를 수행해왔다. 최근 발표된 구조화되지 않은 데이터로부터 복잡한 관계 추론을 수행하는 심층신경망(deep neural networks)은 관계추론(relational reasoning)의 시도를 이해하는데 기대할 만한 접근법을 보여주고 있다. 그 첫 번째는 관계추론을 위한 간단한 신경망 모듈(A simple neural network module for relational reasoning) 인 RN(Relation Networks)이고, 두 번째는 시각적 관찰을 기반으로 실제대상의 미래 상태를 예측하는 범용 목적의 VIN(Visual Interaction Networks)이다. 관계 추론을 수행하는 이들 심층신경망(deep neural networks)은 세상을 객체(objects)와 그들의 관계(their relations)라는 체계로 분해하고, 신경망(neural networks)이 피상적으로는 매우 달라 보이지만 근본적으로는 공통관계를 갖는 장면들에 대하여 객체와 관계라는 새로운 결합(combinations)을 일반화할 수 있는 강력한 추론 능력(powerful ability to reason)을 보유할 수 있다는 것을 보여주고 있다. 본 논문에서는 관계 추론을 수행하는 심층신경망(deep neural networks) 중에서 Sort-of-CLEVR 데이터 셋(dataset)을 사용하여 RN(Relation Networks)의 성능을 재현 및 관찰해 보았으며, 더 나아가 파라미터(parameters) 튜닝을 통하여 RN(Relation Networks) 모델의 성능 개선방법을 제시하여 보았다.

• Journal of Information Technology Services
• /
• 제16권4호
• /
• pp.149-160
• /
• 2017

Sentiment analysis is the process of determining whether a piece of document, text or conversation is positive, negative, neural or other emotion. Sentiment analysis has been applied for several real-world applications, such as chatbot. In the last five years, the practical use of the chatbot has been prevailing in many field of industry. In the chatbot applications, to recognize the user emotion, sentiment analysis must be performed in advance in order to understand the intent of speakers. The specific emotion is more than describing positive or negative sentences. In light of this context, we propose deep learning models for conducting multi-class sentiment analysis for identifying speaker's emotion which is categorized to be joy, fear, guilt, sad, shame, disgust, and anger. Thus, we develop convolutional neural network (CNN), long short term memory (LSTM), and multi-layer neural network models, as deep neural networks models, for detecting emotion in a sentence. In addition, word embedding process was also applied in our research. In our experiments, we have found that long short term memory (LSTM) model performs best compared to convolutional neural networks and multi-layer neural networks. Moreover, we also show the practical applicability of the deep learning models to the sentiment analysis for chatbot.

• Computational Structural Engineering
• /
• 제9권2호
• /
• pp.93-101
• /
• 1996

An artificial neural network is a computational model that mimics the biological system of the brain and it consists of a number of interconnected processing units where it can reasonably infer by them. Because the neural network is particularly useful for evaluating systems with a multitude of nonlinear variables, it can be used in experimental results predictions, in structural planning and in optimum design of structures. This paper describes the basic theory related to the neural networks and discusses the applicability of neural networks to predict the ultimate shear capacity of the precast concrete vertical joints by comparing the neural networks with a conventional method such as regression.

• International journal of advanced smart convergence
• /
• 제1권2호
• /
• pp.30-33
• /
• 2012

This paper propose a new design of fuzzy neural networks based on hard partition to generate the rules of the networks. For this we use hard c-means (HCM) clustering algorithm. The premise part of the rules of the proposed networks is realized with the aid of the hard partition of input space generated by HCM clustering algorithm. The consequence part of the rule is represented by polynomial functions. And the coefficients of the polynomial functions are learned by BP algorithm. The number of the hard partition of input space equals the number of clusters and the individual partitioned spaces indicate the rules of the networks. Due to these characteristics, we may alleviate the problem of the curse of dimensionality. The proposed networks are evaluated with the use of numerical experimentation.

• Journal of the Korean Data and Information Science Society
• /
• 제12권2호
• /
• pp.1-10
• /
• 2001

Neural networks we increasingly being seen as an addition to the statistics toolkit which should be considered alongside both classical and modern statistical methods. Neural networks are usually useful for classification and function estimation. In this paper we concentrate on function estimation using neural networks with weight decay factor The use of weight decay seems both to help the optimization process and to avoid overfitting. In this type of neural networks, the problem to decide the number of hidden nodes, weight decay parameter and iteration number of learning is very important. It is called the optimization of weight decay neural networks. In this paper we propose a automatic optimization based on genetic algorithms. Moreover, we compare the weight decay neural network automatically learned according to automatic optimization with ordinary neural network, projection pursuit regression and support vector machines.

• The Journal of the Acoustical Society of Korea
• /
• 제37권2호
• /
• pp.118-128
• /
• 2018

In this paper, we have studied how to search an underwater object by learning the image generated by the side scan sonar in the convolution neural network. In the method of human side analysis of the side scan image or the image, the convolution neural network algorithm can enhance the efficiency of the analysis. The image data of the side scan sonar used in the experiment is the public data of NSWC (Naval Surface Warfare Center) and consists of four kinds of synthetic underwater objects. The convolutional neural network algorithm is based on Faster R-CNN (Region based Convolutional Neural Networks) learning based on region of interest and the details of the neural network are self-organized to fit the data we have. The results of the study were compared with a precision-recall curve, and we investigated the applicability of underwater object detection in convolution neural networks by examining the effect of change of region of interest assigned to sonar image data on detection performance.