• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.324-326
• /
• 2012

기계 학습에서 입력 데이터의 차원을 줄이는 문제(dimension reduction)는 매우 중요한 문제 중의 하나이다. 입력 변수의 차원이 늘어남에 따라 처리해야하는 연산의 수와 계산 복잡도가 급격히 늘어나기 때문이다. 이를 해결하기 위하여 다수의 기계 학습 알고리즘은 명시적으로 차원을 줄이거나(feature selection), 데이터에 약간의 연산을 가하여 차원이 작은 새로운 입력 데이터를 만든다(feature extraction). 반면 사람이 여러 종류의 고차원 센서 데이터를 입력받아 빠른 시간 안에 정확하게 정보를 처리할 수 있는 가장 큰 이유 중 하나는 실시간으로 판단하여 가장 필요한 정보에 집중하기 때문이다. 본 연구는 사람의 정보 처리 과정을 기계 학습 알고리즘에 반영하여, 집중도를 이용하여 효율적으로 데이터를 처리하는 방법을 제시한다. 이 성질을 시각 하이퍼네트워크 모델에 반영하여, 효율적으로 고차원 입력 데이터를 다루는 방법을 제안한다. 실험에서는 시각 하이퍼네트워크를 이용하여 고차원의 이미지 데이터에서 행동을 분류하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.256-258
• /
• 2000

최근 들어, 여러 기계학습 알고리즘이 문서 분류와 여과에 사용되고 있다. 특히 AdaBoost와 같은 부스팅 알고리즘은 실세계의 문서 데이터에 사용되었을 때 비교적 좋은 성능을 보이는 것으로 알려져 있다. 그러나 지금까지의 부스팅 알고리즘은 모두 단어의 존재 여부만을 가지고 판단하는 분류자를 기반으로 하고 있기 때문에 가중치 정보를 충분히 사용할 수 없다는 단점이 있다. 이 논문에서는 나이브 베이스를 사용한 부스팅 알고리즘은 단어의 가중치 정보를 효율적으로 사용할 수 있을 뿐 아니라. 확률적으로도 의미있는 신뢰도(confidence ratio)를 생성 할 수 있기 때문이다. TREC-7과 TREC-8의 정보 여과 트랙(filtering track)에 대해서 실험한 결과 좋은 성능을 보여주었다.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.4 s.42
• /
• pp.17-25
• /
• 2006

An intelligent game has been studied for some time, and the main purpose of the study was to win against human by enhancing game skills. But some commercial games rather focused on adaptation of the user's behavior in order to bring interests on the games. In this study, we are suggesting an adaptive reinforcement learning algorithm, which focuses on the adaptation of user behavior. We have designed and developed the Othello game, which provides large state spaces. The evaluation of the experiment was done by playing two reinforcement learning algorithms against Min-Max algorithm individually. And the results show that our approach is playing more improved learning rate, than the previous reinforcement learning algorithm.

• Information and Communications Magazine
• /
• v.31 no.11
• /
• pp.52-57
• /
• 2014

Deep learning은 많은 수의 계층으로 이루어진 깊은 신경망을 학습하기 위한 연구 분야이다. 지난 수 년 동안 deep learning은 다양한 분야에 적용되어 기존 방법들을 능가하는 높은 성능을 보였으며, 그 결과 기계학습 및 패턴인식 분야에서 가장 중요한 기술적 트랜드가 되어가고 있다. 깊은 신경망의 장점과 그 동안 깊은 신경망의 학습이 어려웠던 이유를 설명하고 이러한 어려움을 극복한 새로운 알고리즘들을 소개한다. 마지막으로 deep learning의 성공적 응용 사례에 대해 소개한다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.3
• /
• pp.71-80
• /
• 2021

The selection of an appropriate neural network algorithm is an important step for accurate data prediction in machine learning. Many algorithms based on basic artificial neural networks have been devised to efficiently predict future data. These networks include deep neural networks (DNNs), recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and gated recurrent unit (GRU) neural networks. Developers face difficulties when choosing among these networks because sufficient information on their performance is unavailable. To alleviate this difficulty, we evaluated the performance of each algorithm by comparing their errors and processing times. Each neural network model was trained using a tax dataset, and the trained model was used for data prediction to compare accuracies among the various algorithms. Furthermore, the effects of activation functions and various optimizers on the performance of the models were analyzed The experimental results show that the GRU and LSTM algorithms yields the lowest prediction error with an average RMSE of 0.12 and an average R2 score of 0.78 and 0.75 respectively, and the basic DNN model achieves the lowest processing time but highest average RMSE of 0.163. Furthermore, the Adam optimizer yields the best performance (with DNN, GRU, and LSTM) in terms of error and the worst performance in terms of processing time. The findings of this study are thus expected to be useful for scientists and developers.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.4
• /
• pp.595-600
• /
• 2024

As the use of artificial intelligence technologies such as machine learning increases in research fields that predict learning outcomes or optimize learning pathways, the use of artificial intelligence in education is gradually making progress. This research is gradually evolving into more advanced artificial intelligence methods such as deep learning and reinforcement learning. This study aims to improve the method of predicting future learning performance based on the learner's past learning performance-history data. Therefore, to improve prediction performance, we propose conditional probability applying the Markov Chain method. This method is used to improve the prediction performance of the classifier by allowing the learner to add learning history data to the classification prediction in addition to classification prediction by machine learning. In order to confirm the effectiveness of the proposed method, a total of more than 30 experiments were conducted per algorithm and indicator using empirical data, 'Teaching aid-based early childhood education learning performance data'. As a result of the experiment, higher performance indicators were confirmed in cases using the proposed method than in cases where only the classification algorithm was used in all cases.

• Journal of Digital Convergence
• /
• v.16 no.10
• /
• pp.205-212
• /
• 2018

With the development of high performance CPU / GPU, artificial intelligence algorithms such as deep neural networks, and a large amount of data, machine learning has been extended to various applications. In particular, a large amount of data collected from the Internet of Things, social network services, web pages, and public data is accelerating the use of machine learning. Learning data sets for machine learning exist in various formats according to application fields and data types, and thus it is difficult to effectively process data and apply them to machine learning. Therefore, this paper studied a method for building a learning data set for machine learning in accordance with standardized procedures. This paper first analyzes the requirement of learning data set according to problem types and data types. Based on the analysis, this paper presents the reference model to build learning data set for machine learning applications. This paper presents the target standardization organization and a standard development strategy for building learning data set.

• Journal of Digital Convergence
• /
• v.16 no.5
• /
• pp.221-229
• /
• 2018

Machine learning and artificial intelligence are core technologies for the 4th industrial revolution. However, it is difficult for the general public to get familiar with those technologies because most people lack programming ability. Thus, we developed a Graphic User Interface(GUI) to overcome this obstacle. We adopted TensorFlow and used .Net of Microsoft for the develop. With this new GUI, users can manage data, apply algorithms, and run machine learning without coding ability. We hope that this development will be used as a basis for developing artificial intelligence in various fields.

• Journal of KIISE
• /
• v.41 no.11
• /
• pp.911-920
• /
• 2014

In this paper, we introduce an automatic scoring system for middle-school level writing test based on using machine learning techniques. We discuss overall process and features for building an automatic English writing scoring system. A "concept answer" which represents an abstract meaning of text is newly introduced in order to evaluate the elaboration of a student's answer. In this work, multiple machine learning algorithms are adopted for scoring English writings. We suggest a decision process "optimal combination" which optimally combines multiple outputs of machine learning algorithms and generates a final single output in order to improve the performance of the automatic scoring. By experiments with actual test data, we evaluate the performance of overall automated English writing scoring system.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.3
• /
• pp.57-67
• /
• 2018

The ensemble is a unified approach used for getting better performance by using multiple algorithms in machine learning. In this paper, we introduce boosting and bagging, which have been widely used in ensemble techniques, and design a method using support vector regression, radial basis function network, Gaussian process, and multilayer perceptron. In addition, our experiment was performed by adding a recurrent neural network and MOHID numerical model. The drifter data used for our experimental verification consist of 683 observations in seven regions. The performance of our ensemble technique is verified by comparison with four algorithms each. As verification, mean absolute error was adapted. The presented methods are based on ensemble models using bagging, boosting, and machine learning. The error rate was calculated by assigning the equal weight value and different weight value to each unit model in ensemble. The ensemble model using machine learning showed 61.7% improvement compared to the average of four machine learning technique.