• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.920-926
• /
• 2004

The human being receives a new information from outside and the information shows gradual oblivion with time. But the information remains in memory and isn't forgotten for a long time if the information is read several times over. For example, we assume that we memorize a telephone number when we listen and never remind we may forget it soon, but we commit to memory long time by repeating. If the human being received new information with strong stimulus, it could remain in memory without recalling repeatedly. The moments of almost losing one's life in an accident or getting a stroke of luck are rarely forgiven. The human being can keep memory for a long time in spite of the limit of memory for the mechanism mentioned above. In this paper, we propose a model to explain the mechanism mentioned above using a neural network and fuzzy.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.15-30
• /
• 2023

Recently, generative models based on the Transformer architecture, such as ChatGPT, have been gaining significant attention. The Transformer architecture has been applied to various neural network models, including Google's BERT(Bidirectional Encoder Representations from Transformers) sentence generation model. In this paper, a method is proposed to create a text binary classification model for determining whether a comment on Korean movie review is positive or negative. To accomplish this, a pre-trained multilingual BERT sentence generation model is fine-tuned and transfer learned using a new Korean training dataset. To achieve this, a pre-trained BERT-Base model for multilingual sentence generation with 104 languages, 12 layers, 768 hidden, 12 attention heads, and 110M parameters is used. To change the pre-trained BERT-Base model into a text classification model, the input and output layers were fine-tuned, resulting in the creation of a new model with 178 million parameters. Using the fine-tuned model, with a maximum word count of 128, a batch size of 16, and 5 epochs, transfer learning is conducted with 10,000 training data and 5,000 testing data. A text sentiment binary classification model for Korean movie review with an accuracy of 0.9582, a loss of 0.1177, and an F1 score of 0.81 has been created. As a result of performing transfer learning with a dataset five times larger, a model with an accuracy of 0.9562, a loss of 0.1202, and an F1 score of 0.86 has been generated.

• 전기의세계
• /
• v.27 no.5
• /
• pp.33-54
• /
• 1978

(차례) 1.산학협동심포지업 (1)우리나라에서의 연구개발과 산학협동 (2)산학협동과 산업계의 역할 (3)산학협동의 현황과 진로 2.학술회의A (1)전력게통의 계층구조와 협조원리에 관한 연구 (2)2중층괴상회전자 유도전동기의 이론해석 (3)초고주파가열장치에 사용하는 철공진변압기의 해석적 설계 (4)한국전기기시험연구소 대전력단락 시험설비설계 (5)직류전동기제어를 위한 Thyristor Chopper정류회로에 관한 연구 (6)선로의 개폐정보를 포함하는 전력계통의 상태추정 (7)단일신경세포에 대한 ITEM 신호 특성 3.학술회의B (1)MMM-1 Computer System의 설계 및 제작 (2)Adaptive Delta Modulation System의 성능비교 연구 (3)6GHZ FMD마이크로파 무선전송장치의 개발 (4)적선도에 의한 회로망함수의 결정 (5)동맥혈압의 해석과 그의 전기적 유사모델 (6)피부감각의 정보전달 특성에 관하여 (7)선형직접회로의 공정설계 및 그 특성 조성 (8)DH L.D의 전기적포화현상에 관한 이론적 해석 (9)Potocoupler를 이용한 Isolator 4.학술회의C (1)Al-Al$_{2}$O$_{3}$ -Al박막구조의 전기적 특성 (2)이종금속에 샌드위치된 고분자물질의 단락전조 (3)유전체가 일부체워진 직 6면체의 캐비티의 다중모오드 해석 (4)반도체 가스 검지소자의 제조 및 그의 전기적 특성 (5)실리콘 산화공정에 대한 실험적 고찰 (6)진공증착법에 의한 InSb 박막제도에서 열처리효과 (7)(Ba$_{1}$-xBix) Tio$_{3}$ PTC thermistor의 첨가량의 최적건안 (8)금속박막증착시 두께조절 5.특별강연회 (1)일본에 있어서의 절력계통공학연구 (2)Linear Motor의 최근개발동향량도 높았다. valine과 leucine 및 aspartic acid, glycine과 glutamic acid, leucine과 aspartic acid 간에는 고도의 정상관, glycine과 serine, valine과 phenylalanine, threonine과 proline, phenylalanine과 arginine, methionine과 glutamic acid, histidine과 lysine 간에는 유의 정상관, 그리고 isoleucine과 lysine 간에는 유의한 부상관이 있었다. 4. lysine 함량은 단백질 함량과 정산곤, isoleucine 함량은 단빅질 함량과 부상관을 보였으며, alanine, valine, leucine 함량은 지방함량과 각각 유의한 정산관을 보였다. 5. 대두 단백질은 7.5% acrylamide gel 전기영동에 의해 품종에 따라 12～16개의 구성분으로 분리되었으며, 이들중 주구성분들은 상대이동도가 0.06(a), 0.14(b). 0.24(d) 이었고, 구성분 b의 함량이 품종간에 가장 변이가 컸으며, 구성분 b는 그밖의 주요 구성분들의 함량과 부의 상관이 있었고, 구성분 a는 단백질 함량과 정상관이 있었다. 6. 종실단백질 구성분들의 조합 특성 면에서 공시 86품종은 11개 유형군으로 분류되었으며, 우리나라와 일본품종은 미국품종에 비해 단백질구성분 조성이 훨씬 다양하였다. 7. 이동도가 매우 빠른 단백질 구성분 o(Rm 0.77) p(Rm 0.81)를 모두 갖고 있는 품종은 3품종, 모두 갖고 있지 않은 품종은 1품종이었고, 나머지 82품종은 o나 p중 한 구성분을 갖고 있었으며 그 분포율은 30 : 65 이었는데 미국계 품종은 우리나라 품종에 비해 구성분 o를 간고 있는 비율이 현저히 적었다. 8. 대두 종실은 개화후 22일까지 완만히, 그 이후 20～30일간 급속히

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.2
• /
• pp.15-23
• /
• 2017

The person Re-identification is the most challenging part of computer vision due to the significant changes in human pose and background clutter with occlusions. The picture from non-overlapping cameras enhance the difficulty to distinguish some person from the other. To reach a better performance match, most methods use feature selection and distance metrics separately to get discriminative representations and proper distance to describe the similarity between person and kind of ignoring some significant features. This situation has encouraged us to consider a novel method to deal with this problem. In this paper, we proposed an enhanced recurrent neural network with three-tier hierarchical network for person re-identification. Specifically, the proposed recurrent neural network (RNN) model contain an iterative expectation maximum (EM) algorithm and three-tier Hierarchical network to jointly learn both the discriminative features and metrics distance. The iterative EM algorithm can fully use of the feature extraction ability of convolutional neural network (CNN) which is in series before the RNN. By unsupervised learning, the EM framework can change the labels of the patches and train larger datasets. Through the three-tier hierarchical network, the convolutional neural network, recurrent network and pooling layer can jointly be a feature extractor to better train the network. The experimental result shows that comparing with other researchers' approaches in this field, this method also can get a competitive accuracy. The influence of different component of this method will be analyzed and evaluated in the future research.