• Electronics and Telecommunications Trends
• /
• v.31 no.3
• /
• pp.131-141
• /
• 2016

최근 알파고를 통해 인공지능 기술이 전 세계인의 이목을 집중시켰던 반면, 인공지능 연구자들은 인공지능 부활에 결정적 역할을 한 딥러닝 기술에 주목하고 있다. 딥러닝은 다계층 인공신경망 기반의 기계학습 기술로서 최근 컴퓨터 비전, 음성인식, 자연어 처리 분야에서 인식 성능을 높이는 데 중요한 역할을 하고 있다. 딥러닝 기술을 이용하여 기계가 수천만장의 이미지를 학습하여 객체를 인식하게 하고, 수천 시간의 음성 데이터를 학습하여 사람의 말을 알아듣게 처리하는 데에는 다수의 고성능 컴퓨터가 필요하다. 따라서 딥러닝에는 다수의 컴퓨터를 효율적으로 이용하기 위한 분산처리 기술이 필수적이며 관련 연구들이 활발히 진행되고 있다. 이에 본고는 다중 컴퓨터 노드들에서 딥러닝 모델을 분산처리할 수 있는 기존의 프레임워크들을 비교 분석하고 딥러닝 분산처리 기술에 대한 발전 방향을 전망한다.

• Journal of Digital Contents Society
• /
• v.19 no.2
• /
• pp.415-423
• /
• 2018

In recent years, Computer-based learning, such as machine learning and deep learning in the computer field, is attracting attention. They start learning from the lowest level and propagate the result to the highest level to calculate the final result. Research literature has shown that systematic learning and growth can yield good results. However, systematic models based on systematic models are hard to find, compared to various and extensive research attempts. To this end, this paper proposes the first TNT(Transitive Nested Triangle)model, which is a growth and fusion model that can be used in various aspects. This model can be said to be a recursive model in which each function formed through geometric forms an organic hierarchical relationship, and the result is used again as they grow and converge to the top. That is, it is an analytical method called 'Horizontal Sibling Merges and Upward Convergence'. This model is applicable to various aspects. In this study, we focus on explaining the TNT model.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.11
• /
• pp.107-112
• /
• 2024

In this paper, we propose a method to detect abnormal power usage conditions in domestic franchise convenience stores, by detecting cases where the temperature of the refrigeration or freezer equipment operates outside the normal range and classifying detailed abnormal situations. Compared to normal data, abnormal data is very small, and the amount of data varies depending on the type of abnormality, leading to a data imbalance issue. The proposed method employs a hierarchical structure that combines a time series classification algorithm with kNN, addressing the data imbalance problem and enabling classification using relatively small amounts of data. In this paper, we conducted an experiment by independently constructing our own dataset to validate the proposed methodology.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_2
• /
• pp.1239-1249
• /
• 2018

Optical remote sensing sensors provide visually more familiar images than radar images. However, it is difficult to discriminate sea ice types in optical images using spectral information based machine learning algorithms. This study addresses two topics. First, we propose a semantic segmentation which is a part of the state-of-the-art deep learning algorithms to identify ice types by learning hierarchical and spatial features of sea ice. Second, we propose a new approach by combining of semi-supervised and active learning to obtain accurate and meaningful labels from unlabeled or unseen images to improve the performance of supervised classification for multiple images. Therefore, we successfully added new labels from unlabeled data to automatically update the semantic segmentation model. This should be noted that an operational system to generate ice type products from optical remote sensing data may be possible in the near future.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.6
• /
• pp.1571-1580
• /
• 1999

When a hierarchical structure is derived from data set for data mining and machine learning, using a conceptual clustering algorithm, one of the unsupervised learning paradigms, it is not unusual to have a different set of outcomes with respect to the order of processing data objects. To overcome this problem, the first classification process is proceeded to construct an initial partition. The partition is expected to imply the possible range in the number of final classes. We apply center sorting to the data objects in the classes of the partition for new data ordering and build a new partition using ITERATE clustering procedure. We developed an algorithm, REIT that leads to the final partition with stable and best partition score. A number of experiments were performed to show the minimization of order bias effects using the algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.4
• /
• pp.355-359
• /
• 2014

In this paper, we proposed the new fuzzy pattern classifier which combines several fuzzy models with simple consequent parts hierarchically. The basic component of the proposed fuzzy pattern classifier with hierarchical structure is a fuzzy model with simple consequent part so that the complexity of the proposed fuzzy pattern classifier is not high. In order to analyze and divide the input space, we use Fuzzy C-Means clustering algorithm. In addition, we exploit Conditional Fuzzy C-Means clustering algorithm to analyze the sub space which is divided by Fuzzy C-Means clustering algorithm. At each clustered region, we apply a fuzzy model with simple consequent part and build the fuzzy pattern classifier with hierarchical structure. Because of the hierarchical structure of the proposed pattern classifier, the data distribution of the input space can be analyzed in the macroscopic point of view and the microscopic point of view. Finally, in order to evaluate the classification ability of the proposed pattern classifier, the machine learning data sets are used.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1995.10a
• /
• pp.280-283
• /
• 1995

계층형 신경회로망은 학습능력이나 비선형사상능력을 가지고 있고, 그 특징을 이용하여 패턴인식이나 동정 및 제어 등에의 적용이 시도되어 성과를 올리고 있다. 현재, 그 학습법으로 널리 이용되고 있는 것이 역전파학습법으로 최급 강하법이나 공액경사법 등의 최적화 방법이 적용되고 있지만, 학습에 많은 시간이 걸리는 점, 국소적 최적해(local minima)에 해의 수렴이 이루어져 오차가 충분히 작게 되지 않는 점 등이 문제점으로 지적되고 있다. 본 논문에서는 Hu에 의해 고안된 random 탐색법과 조합된 random tabu 탐색법으로 최적결합계수를 구하는 학습알고리즘으로, 국소적 최적해에 수렴하는 것을 방지하고, 수렴정도를 개선하는 새로운 방법을 이용하여 회전기계의 이상진동진단에 적용가능성을 검토하고 오차역전파법에 의한 진단결과와 비교검토한다.

• The KIPS Transactions:PartB
• /
• v.13B no.2 s.105
• /
• pp.171-178
• /
• 2006

Most approaches for extracting hypernyms of a noun from its definitions in an MRD rely on lexical patterns compiled by human experts. Not only these approaches require high cost for compiling lexical patterns but also it is very difficult for human experts to compile a set of lexical patterns with a broad-coverage because in natural languages there are various expressions which represent same concept. To alleviate these problems, this paper proposes a new method for extracting hypernyms of a noun from its definitions in an MRD. In proposed approach, we use only syntactic (part-of-speech) patterns instead of lexical patterns in identifying hypernyms to reduce the number of patterns with keeping their coverage broad. Our experiment has shown that the classification accuracy of the proposed method is 92.37% which is significantly much better than that of previous approaches.

• KIISE Transactions on Computing Practices
• /
• v.23 no.2
• /
• pp.104-109
• /
• 2017

We propose a new machine learning algorithm which analyzes daily activity patterns of users from multi-modal wearable sensor data. The proposed model learns and extracts activity patterns using input from wearable devices in real-time. Inspired by cue integration of human's property, we constructed gated multi-modal neural networks which integrate wearable sensor input data selectively by using gate modules. For the experiments, sensory data were collected by using multiple wearable devices in restaurant situations. As an experimental result, we first show that the proposed model performs well in terms of prediction accuracy. Then, the possibility to construct a knowledge schema automatically by analyzing the activation patterns in the middle layer of our proposed model is explained.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.209-212
• /
• 2017

고도화된 머신러닝과 딥러닝 기술은 영상처리, 자연어처리 등의 분야에서 많은 문제를 해결하고 있다. 특히 사용자가 입력한 문장을 분석하고 그에 따른 문장을 생성하는 자연어처리 기술은 기계 번역, 자동 요약, 자동 오류 수정 등에 널리 이용되고 있다. 딥러닝 기반의 자연어처리 기술은 학습을 위해 여러 계층의 신경망을 구성하여 단어 간 의존 관계와 문장 구조를 학습한다. 그러나 학습 과정에서의 계산양이 방대하여 모델을 구성하는데 시간과 비용이 많이 필요하다. 그러나 Word2Vec 모델은 신경망과 유사하게 학습하면서도 선형 구조를 가지고 있어 딥러닝 기반 자연어처리 기술에 비해 적은 시간 복잡도로 고차원의 단어 벡터를 계산할 수 있다. 따라서 본 논문에서는 Word2Vec 모델을 활용하여 한국어 문장을 생성하는 방법을 제시하였다. 본 논문에서는 지정된 문장 템플릿에 유사도가 높은 각 단어들을 적용하여 문장을 구성하는 Word2Vec 모델을 설계하였고, 서로 다른 학습 데이터로부터 생성된 문장을 평가하고 제안한 모델의 활용 방안을 제시하였다.