• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.11
• /
• pp.151-162
• /
• 1994

A new neural network structure called Self-organized Distributed Networks (SODN) is proposed for developing the neural network-based multidimensional system models. The learning with the proposed networks is fast and precise. Such properties are caused from the local learning mechanism. The structure of the networks is combination of dual networks such as self-organized networks and multilayered local networks. Each local networks learns only data in a sub-region. Large number of memory requirements and low generalization capability for the untrained region, which are drawbacks of conventional local network learning, are overcomed in the proposed networks. The simulation results of the proposed networks show better performance than the standard multilayer neural networks and the Radial Basis function(RBF) networks.

• Electronics and Telecommunications Trends
• /
• v.38 no.4
• /
• pp.95-103
• /
• 2023

The importance of the decentralized training with decentralized execution (DTDE) framework is well-known in the study of multiagent reinforcement learning. In many real-world environments, agents cannot share information. Hence, they must be trained in a decentralized manner. However, the DTDE framework has been less studied than the centralized training with decentralized execution framework. One of the main reasons is that many problems arise when training agents in a decentralized manner. For example, DTDE algorithms are often computationally demanding or can encounter problems with non-stationarity. Another reason is the lack of simulation environments that can properly handle the DTDE framework. We discuss current research trends in the DTDE framework.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.941-944
• /
• 2017

심층 학습에 기반을 둔 통계적 언어모형에서 가장 중요한 작업은 단어의 분산 표현(Distributed Representation)이다. 단어의 분산 표현은 단어 자체가 가지는 의미를 다차원 공간에서 벡터로 표현하는 것으로서, 워드 임베딩(word embedding)이라고도 한다. 워드 임베딩을 이용한 심층 학습 기반 통계적 언어모형은 전통적인 통계적 언어모형과 비교하여 성능이 우수한 것으로 알려져 있다. 그러나 워드 임베딩 역시 자료 부족분제에서 벗어날 수 없다. 특히 학습데이터에 나타나지 않은 단어(unknown word)를 처리하는 것이 중요하다. 본 논문에서는 고품질 한국어 워드 임베딩을 위하여 단어의 의미적 계층정보를 이용한 워드 임베딩 방법을 제안한다. 기존연구에서 제안한 워드 임베딩 방법을 그대로 활용하되, 학습 단계에서 목적함수가 입력 단어의 하위어, 동의어를 반영하여 계산될 수 있도록 수정함으로써 단어의 의미적 계층청보를 반영할 수 있다. 본 논문에서 제안한 워드 임베딩 방법을 통해 생성된 단어 벡터의 유추검사(analog reasoning) 결과, 기존 방법보다 5%가 증가한 47.90%를 달성할 수 있었다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.279-284
• /
• 2009

In swarm robot systems, each robot must behaves by itself according to the its states and environments, and if necessary, must cooperates with other robots in order to carry out a given task. Therefore it is essential that each robot has both learning and evolution ability to adapt the dynamic environments. In this paper, reinforcement learning method using many SVM based on structural risk minimization and distributed genetic algorithms is proposed for behavior learning and evolution of collective autonomous mobile robots. By distributed genetic algorithm exchanging the chromosome acquired under different environments by communication each robot can improve its behavior ability. Specially, in order to improve the performance of evolution, selective crossover using the characteristic of reinforcement learning that basis of Cascade SVM is adopted in this paper.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.337-339
• /
• 2016

본 논문에서는 한국어 개체명 인식의 성능 향상을 위하여 워드 임베딩을 활용할 수 있는 방법에 대하여 기술한다. 워드 임베딩이란 문장의 단어의 공기정보를 바탕으로 그 단어의 의미를 벡터로 표현하는 분산표현이다. 이러한 분산 표현은 단어 간의 유의미한 정도를 계산하는데 유용하다. 본 논문에서는 이러한 워드 임베딩을 통하여 단어 벡터들의 코사인 유사도를 통한 개체명 사전 자가 학습 및 매칭 방법을 적용하고, 그 실험 결과를 보고한다.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.3
• /
• pp.131-142
• /
• 2001

다양한 산업체에서 반복적인 특정업무를 수행하는 경우가 흔히 발생한다. 반복되는 오차의 경험치를 근거로 주어진 작업을 추진하는 과정에서 이들 업무의 정밀도제고를 추구함으로써 갖는 성능개선은 사업장의 품질관리와 직결된다. 학습제어의 본래 적용동기는 생산조립라인에 투입되어 반복적인 일을 수행하는 산업로봇의 정밀도 제고이다. 본 논문에서 분산이산시형시스템에서 출발하였으며, 이를 산업용로봇에 적용하기 위하여 수학적으로 모델링한 모의실험을 통하여 알고리즘의 안정성과 반복오차를 줄여가는 과정을 보여 주었다. 입출력정보가 상호간섭 하는 산업용로봇과 같은 복합구조물에서도 모든 시스템(링크)의 정밀도를 만족함을 보여 줌으로써 복합구조물에서 선형반복학습제어의 안정성을 증명하였다.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.1-13
• /
• 2023

As federated learning brings a large paradigm to modern artificial intelligence research, efforts are being made to incorporate federated learning into research in various fields. However, researchers who apply federated learning face the problem of choosing a federated learning framework and benchmark tool suitable for their situation and purpose. This study aims to present guidelines for selection of federated learning frameworks and benchmark tools considering the circumstances of researchers who apply federated learning in practice. In particular, there are three main contributions in this study. First, it generalizes the situation of the researcher applying federated learning by combining it with the goal of federated learning and proposes guidelines for selecting a federated learning framework suitable for each situation. Second, it shows the suitability of selection by comparing the characteristics and performance of each federated learning framework to the researcher. Finally, the limitations of the existing federated learning framework and a plan for real-world federated learning operation are proposed.

• Journal of The Korean Association of Information Education
• /
• v.9 no.1
• /
• pp.79-86
• /
• 2005

With the rapid advance of computer and communication technology, the amount of data transferred is also increasing more than ever. The recent trend of education systems is connecting related information semantically in different systems in order to improve the utilization of computerized information Therefore, Web-based teaching-learning is developing in the ubiquitous learning direction that learners select and organize the contents, time and order of learning by themselves. That is, it is evolving to provide teaching-learning environment adaptive to individual learners' characteristics (their level of knowledge, pattern of study, areas of interest). This paper proposes the efficient evaluation method of learning contents in a mediator for the integration of heterogeneous information resources. This means that the autonomy of a remote server can be preserved to the highest degree. In addition, this paper proposes the adaptive optimization of learning contents such that available storage in a mediator can be highly utilized at any time. In order to differentiate the recent usage of a learning content from the past, the accumulated usage frequency of a learning content decays as time goes by.

• Information and Communications Magazine
• /
• v.31 no.11
• /
• pp.14-26
• /
• 2014

본고는 빅데이터 시대에 새로운 가치를 창출할 수 있는 정보 분석을 위한 기계학습을 설명하고자 한다. 기계학습의 일반적 정의와 특성, 그리고 빅데이터 특성에 의한 기계학습의 변화를 확인하고 특별히 다양한 변화 중에서 분산 및 병렬화를 통한 스케일러블 기계학습을 중점으로 주어진 빅데이터를 효율적으로 분석할 수 있는 다양한 플랫폼들과 프레임워크들을 설명한다. 더불어 실제 다양한 응용 활용을 제공하고 있는 Google API 같은 빅데이터 분석 기계학습 프로젝트들을 통해서 기계학습을 통한 빅데이터 분석에 대한 폭넓은 이해를 전달하고자 한다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.633-641
• /
• 2009

In this paper, we proposed a new pattern classifier which can be incrementally learned, be added new class in learning time, and handle with analog data. Proposed pattern classifier has hierarchical structure and the classification rate is improved by using different metric for each levels. Proposed model is based on the Gaussian ARTMAP which is an artificial neural network model for the pattern classification. We hierarchically constructed the Gaussian ARTMAP and proposed the Principal Component Emphasis(P.C.E) method to be learned different features in each levels. And we defined new metric based on the P.C.E. P.C.E is a method that discards dimensions whose variation are small, that represents common attributes in the class. And remains dimensions whose variation are large. In the learning process, if input pattern is misclassified, P.C.E are performed and the modified pattern is learned in sub network. Experimental results indicate that Hierarchical Gaussian ARTMAP yield better classification result than the other pattern recognition algorithms on variable data set including real applicable problem.