RNN & NLP Application

Size: px
Start display at page:

Download "RNN & NLP Application"

Transcription

1 RNN & NLP Application 강원대학교 IT 대학 이창기

2 차례 RNN NLP application

3 Recurrent Neural Network Recurrent property dynamical system over time

4 Bidirectional RNN Exploit future context as well as past

5 Long Short-Term Memory RNN Vanishing Gradient Problem for RNN LSTM can preserve gradient information

6 LSTM Block Architecture

7 Gated Recurrent Unit (GRU) r t = σ W xr x t + W hr h t 1 + b r z t = σ W xx x t + W hz h t 1 + b z h t = φ W xh x t + W hh r t h t 1 + b h h t = z t h t + 1 z t h t y t = g(w hy h t + b y )

8 차례 RNN NLP application

9 Sequence Labeling RNN, LSTM Word embedding Feature embedding

10 FFNN(or CNN), CNN+CRF (SENNA) y(t-1) y(t ) y(t+1) y(t-1) y(t ) y(t+1) h(t-1) h(t ) h(t+1) h(t-1) h(t ) h(t+1) x(t-1) x(t ) x(t+1) x(t-1) x(t ) x(t+1)

11 RNN, CRF Recurrent CRF y(t-1) y(t ) y(t+1) y(t-1) y(t ) y(t+1) h(t-1) h(t ) h(t+1) x(t-1) x(t ) x(t+1) x(t-1) x(t ) x(t+1) y(t-1) y(t ) y(t+1) h(t-1) h(t ) h(t+1) x(t-1) x(t ) x(t+1)

12 LSTM RNN + CRF LSTM-CRF (KCC 15) y(t-1) y(t ) y(t+1) y(t-1) y(t ) y(t+1) h(t-1) h(t ) h(t+1) x(t-1) x(t ) x(t+1) x(t-1) x(t ) x(t+1) y(t-1) y(t ) y(t+1) f (t ) h(t-1) h(t ) h(t+1) i (t ) o(t ) x(t-1) x(t ) x(t+1) x(t ) C(t) h(t )

13 LSTM-CRF i t = σ W xi x t + W hi h t 1 + W ci c t 1 + b i f t = σ W xf x t + W hf h t 1 + W cf c t 1 + b f c t = f t c t 1 + i t tanh W xc x t + W hc h t 1 + b c o t = σ W xo x t + W ho h t 1 + W co c t + b o h t = o t tanh(c t ) y t = g(w hy h t + b y ) y t = W hy h t + b y s x, y = t=1 T A y t 1, y t + y t log P y x = s x, y log y exp(s(x, y ))

14 GRU+CRF y(t-1) y(t ) y(t+1) h(t-1) h(t ) h(t+1) r t = σ W xr x t + W hr h t 1 + b r x(t-1) x(t ) x(t+1) z t = σ W xz x t + W hz h t 1 + b z h t = φ W xh x t + W hh r t h t 1 + b h h t = z t h t z t h t y t = g(w hy h t + b y ) y t = W hy h t + b y T s x, y = t=1 A y t 1, y t + y t log P y x = s x, y log y exp(s(x, y ))

15 Bi-LSTM CRF Bidirectional LSTM+CRF Bidirectional GRU+CRF Stacked Bi-LSTM+CRF y(t-1) y(t ) y(t+1) bh(t-1) bh(t ) bh(t+1) h(t-1) h(t ) h(t+1) x(t-1) x(t ) x(t+1)

16 Stacked LSTM CRF y(t-1) y(t ) y(t+1) y(t-1) y(t ) y(t+1) bh(t-1) bh(t ) bh(t+1) h2(t-1) h2(t ) h2(t+1) h(t-1) h(t ) h(t+1) h(t-1) h(t ) h(t+1) x(t-1) x(t ) x(t+1) x(t-1) x(t ) x(t+1)

17 LSTM CRF with Context words = CNN + LSTM CRF Bi-LSTM CRF =~ LSTM CRF with Context > LSTM CRF y(t-1) y(t ) y(t+1) h(t-1) h(t ) h(t+1) x(t-2) x(t-1) x(t ) x(t+1) x(t+2)

18 Neural Architectures for NER (Arxiv16) LSTM-CRF model + Char-based Word Representation Char: Bi-LSTM RNN

19 End-to-end Sequence Labeling via Bidirectional LSTM-CNNs-CRF (ACL16) LSTM-CRF model + Char-level Representation Char: CNN

20 NER with Bidirectional LSTM-CNNs (Arxiv16)

21 LSTM RNN 기반한국어감성분석 LSTM RNN-based encoding Sentence embedding 입력 Fully connected NN 출력 GRU encoding 도유사함 h(1) h(2 ) h(t) y x(1) x(2 ) x(t) Data set Model Accuracy Mobile Train: 4543 Test: 500 SVM (word feature) CNN(relu,kernel3,hid50)+Word embedding (word feature) GRU encoding + Fully connected NN LSTM RNN encoding + Fully connected NN 90.93

22 Neural Machine Translation T S 777 항공편은 3 시간 동안 지상 에 있 겠 습니다. </s> flight is on the ground for three hours </s>

23 Recurrent NN Encoder Decoder for Statistical Machine Translation (EMNLP14) GRU RNN Encoding GRU RNN Decoding Vocab: 15,000 (src, tgt)

24 Sequence to Sequence Learning with Neural Networks (NIPS14 Google) Source Voc.: 160,000 Target Voc.: 80,000 Deep LSTMs with 4 layers Train: 7.5 epochs (12M sentences, 10 days with 8- GPU machine)

25 Neural MT by Jointly Learning to Align and Translate (ICLR15) GRU RNN + Alignment Encoding GRU RNN Decoding Vocab: 30,000 (src, tgt) Train: 5 days

26 Abstractive Text Summarization ( 한글및한국어 16) RNN_search+input_feeding+CopyNet 로드킬로숨진친구의곁을지키는길고양이의모습이포착되었다.

27 End-to-End 한국어형태소분석 ( 동계학술대회 16) Attention + Input-feeding + Copying mechanism

28 Sequence-to-sequence 기반한국어구구조구문분석 ( 한글및한국어 16) NP y t-1 y t NP NP 43/SN + 국 /NNG 참가 /NNG h2 t-1 h2 t h1 t-1 h1 t (NP (NP 43/SN + 국 /NNG) (NP 참가 /NNG)) 입력예시 1 43/SN 국 /NNG <sp> 참가 /NNG c t 입력예시 2 입력 정답 RNN-search[7] (Beam size 10) RNN-search + Input-feeding + Dropout (Beam size 10) 4 3 <SN> 국 <NNG> <sp> 참가 <NNG> 선생 <NNG> 님 <XSN> 의 <JKG> <sp> 이야기 <NNG> <sp> 끝나 <VV> 자 <EC> <sp> 마치 <VV> 는 <ETM> <sp> 종 <NNG> 이 <JKS> <sp> 울리 <VV> 었 <EP> 다 <EF>. <SF> (S (S (NP_SBJ (NP_MOD XX ) (NP_SBJ XX ) ) (VP XX ) ) (S (NP_SBJ (VP_MOD XX ) (NP_SBJ XX ) ) (VP XX ) ) ) (S (VP (NP_OBJ (NP_MOD XX ) (NP_OBJ XX ) ) (VP XX ) ) (S (NP_SBJ (VP_MOD XX ) (NP_SBJ XX ) ) (VP XX ) ) ) (S (S (NP_SBJ (NP_MOD XX ) (NP_SBJ XX ) ) (VP XX ) ) (S (NP_SBJ (VP_MOD XX ) (NP_SBJ XX ) ) (VP XX ) ) ) GRU GRU GRU GRU GRU GRU x 1 x 2 x T Attention + Input-feeding

29 Sequence-to-sequence 기반한국어구구조구문분석 ( 한글및한국어 16) 모델 F1 스탠포드구문분석기 [13] 버클리구문분석기 [13] 형태소 + <sp> RNN-search[7] (Beam size 10) RNN-search[7] (Beam size 10) 87.34(baseline) 87.65*(+0.31) 87.69(+0.35) 88.00*(+0.66) 형태소의음절 + 품사태그 + <sp> RNN-search + Input-feeding (Beam size 10) RNN-search + Input-feeding + Dropout (Beam size 10) 88.23(+0.89) 88.68*(+1.34) 88.78(+1.44) 89.03*(+1.69)

30

31 Neural Responding Machine for Short-Text Conversation (ACL 15)

32 Neural Responding Machine cont d

33 실험결과 (ACL 15)

34 Short-Text Conversation ( 동계학술대회 16) - Data: 클리앙 아무거나질문게시판 - 77,346 질문 - 응답쌍 - 학습 : 개발 : 평가 = 8:1:1

35 이미지캡션생성소개 이미지내용이해 이미지내용을설명하는캡션자동생성 이미지인식 ( 이해 ) 기술 + 자연어처리 ( 생성 ) 기술 활용분야 이미지검색 맹인들을위한사진설명, 네비게이션 유아교육,

36 기존연구 Multimodal RNN (M-RNN) [2] Baidu CNN + vanilla RNN CNN: VGGNet Neural Image Caption generator (NIC) [4] Google CNN + LSTM RNN CNN: GoogLeNet Deep Visual-Semantic alignments (DeepVS) [5] Stanford University RCNN + Bi-RNN alignment (training) CNN + vanilla RNN CNN: AlexNet

37 AlexNet, VGGNet

38 RNN 을이용한이미지캡션생성 CNN + RNN ( 동계학술대회 15) CNN: VGGNet 15 번째 layer (4096 차원 ) RNN: GRU (LSTM RNN 의변형 ) Hidden layer unit: 500, 1000 (Best) Multimodal layer unit: 500, 1000 (Best) Word embedding SENNA: 50 차원 (Best) Word2Vec: 300 차원 Data set Flickr 8K : 8000 이미지 * 이미지캡션 5 문장 6000 학습, 1000 검증, 1000 평가 Flickr 30K : 이미지 * 이미지캡션 5 문장 학습, 1014 검증, 1000 평가 4 가지모델실험 GRU-DO1, GRU-DO2, GRU-DO3, GRU-DO4

39 W t+1 Softmax Multimodal CNN GRU Image Embedding GRU-DO1 GRU-DO2 W t W t+1 W t+1 Softmax Softmax Multimodal CNN Multimodal CNN GRU Image GRU Image Embedding Embedding GRU-DO3 GRU-DO4 W t W t

40 RNN 을이용한이미지캡션생성 ( 동계학술대회 15) Flickr 8K B-1 B-2 B-3 B-4 m-rnn (Baidu)[2] DeepVS (Stanford)[5] NIC (Google)[4] Ours-GRU-DO Ours-GRU-DO Ours-GRU-DO Ours-GRU-DO Flickr 30K B-1 B-2 B-3 B-4 m-rnn (Baidu)[2] DeepVS (Stanford)[5] NIC (Google)[4] Ours-GRU-DO Ours-GRU-DO Ours-GRU-DO Ours-GRU-DO W t+1 W t+1 W t+1 Softmax Softmax Softmax Multimodal CNN Multimodal CNN Multimodal CNN GRU Image GRU Image GRU Image Embedding Embedding Embedding W t W t W t

41 Flickr30k 실험결과 A black and white dog is jumping in the grass A group of people in the snow Two men are working on a roof

42 신규데이터 A large clock tower in front of a building A man and a woman are playing with a sheep A man in a field throwing a frisbee A little boy holding a white frisbee

43 한국어이미지캡션생성 W t+1 Softmax Multimodal CNN 한어린소녀가풀로덮인들판에서있다 건물앞에서있는한남자 구명조끼를입은한작은소녀가웃고있다 GRU Image Embedding 분홍색개를데리고있는한여자와한여자 W t

44 Residual Network + 한국어이미지캡션생성 ( 동계학술대회 16)

딥러닝NLP응용_이창기

딥러닝NLP응용_이창기 딥러닝과 자연어처리 응용 강원대학교 IT대학 이창기 차례 딥러닝최신기술소개 딥러닝기반의자연어처리 Classification Problem Sequence Labeling Problem Sequence-to-Sequence Learning Pointer Network Recurrent Neural Network Many NLP problems can be viewed

More information

Structural SVMs 및 Pegasos 알고리즘을 이용한 한국어 개체명 인식

Structural SVMs 및 Pegasos 알고리즘을 이용한 한국어 개체명 인식 딥러닝 기반의 자연어처리 기술 강원대학교 IT대학 이창기 차례 자연어처리소개 딥러닝소개 딥러닝기반의자연어처리 Classification Problem Sequence Labeling Problem Sequence-to-Sequence Learning Pointer Network Machine Reading Comprehension 자연어처리 자연언어 인공언어에대응되는개념

More information

Structural SVMs 및 Pegasos 알고리즘을 이용한 한국어 개체명 인식

Structural SVMs 및 Pegasos 알고리즘을 이용한 한국어 개체명 인식 Deep Learning 차례 현재딥러닝기술수준소개 딥러닝 딥러닝기반의자연어처리 Object Recognition https://www.youtube.com/watch?v=n5up_lp9smm Semantic Segmentation https://youtu.be/zjmtdrbqh40 Semantic Segmentation VGGNet + Deconvolution

More information

<4D6963726F736F667420576F7264202D20B1E2C8B9BDC3B8AEC1EE2DC0E5C7F5>

<4D6963726F736F667420576F7264202D20B1E2C8B9BDC3B8AEC1EE2DC0E5C7F5> 주간기술동향 2016. 5.18. 컴퓨터 비전과 인공지능 장혁 한국전자통신연구원 선임연구원 최근 많은 관심을 받고 있는 인공지능(Artificial Intelligence: AI)의 성과는 뇌의 작동 방식과 유사한 딥 러닝의 등장에 기인한 바가 크다. 이미 미국과 유럽 등 AI 선도국에서는 인공지능 연구에서 인간 뇌 이해의 중요성을 인식하고 관련 대형 프로젝트들을

More information

Delving Deeper into Convolutional Networks for Learning Video Representations - Nicolas Ballas, Li Yao, Chris Pal, Aaron Courville arXiv:

Delving Deeper into Convolutional Networks for Learning Video Representations  -   Nicolas Ballas, Li Yao, Chris Pal, Aaron Courville  arXiv: Delving Deeper into Convolutional Networks for Learning Video Representations Nicolas Ballas, Li Yao, Chris Pal, Aaron Courville arxiv: 1511.06432 Il Gu Yi DeepLAB in Modu Labs. June 13, 2016 Il Gu Yi

More information

(JBE Vol. 24, No. 1, January 2019) (Special Paper) 24 1, (JBE Vol. 24, No. 1, January 2019) ISSN 2287-

(JBE Vol. 24, No. 1, January 2019) (Special Paper) 24 1, (JBE Vol. 24, No. 1, January 2019)   ISSN 2287- (Special Paper) 24 1 2019 1 (JBE Vol. 24 No. 1 January 2019) https//doi.org/10.5909/jbe.2019.24.1.58 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) a) a) a) b) c) d) A Study on Named Entity Recognition

More information

Naver.NLP.Workshop.SRL.Sogang_Alzzam

Naver.NLP.Workshop.SRL.Sogang_Alzzam : Natra Langage Processing Lab 한국어 ELMo 모델을이용한의미역결정 박찬민, 박영준 Sogang_Azzam Naver NLP Chaenge 서강대학교자연어처리연구실 목차 서론 제안모델 실험 결론 2 서론 의미역결정이란? 문장의술어를찾고, 그술어와연관된논항들사이의의미관계를결정하는문제 논항 : 의미역이부여된각명사구의미역 : 술어에대한명사구의의미역할

More information

Ch 1 머신러닝 개요.pptx

Ch 1 머신러닝 개요.pptx Chapter 1. < > :,, 2017. Slides Prepared by,, Biointelligence Laboratory School of Computer Science and Engineering Seoul National University 1.1 3 1.2... 7 1.3 10 1.4 16 1.5 35 2 1 1.1 n,, n n Artificial

More information

Multi-pass Sieve를 이용한 한국어 상호참조해결 반-자동 태깅 도구

Multi-pass Sieve를 이용한 한국어 상호참조해결 반-자동 태깅 도구 Siamese Neural Network 박천음 강원대학교 Intelligent Software Lab. Intelligent Software Lab. Intro. S2Net Siamese Neural Network(S2Net) 입력 text 들을 concept vector 로표현하기위함에기반 즉, similarity 를위해가중치가부여된 vector 로표현

More information

PowerPoint 프레젠테이션

PowerPoint 프레젠테이션 Visual Search At SK-Planet sk-planet Machine Intelligence Lab. 나상일 1. 개발배경 2. 첫접근방법 3. 개선된방법 A. Visual recognition technology B. Guided search C. Retrieval system 개발배경 개발배경 상품검색을좀더쉽게 Key-word 트렌치코트버튺벨트

More information

2014 한국어문학회 전국학술대회 통일 시대를 위한 한국 어문학의 성찰과 모색 겨나면서 민족어 란 용어가 등장하였다. 오늘의 학술대회 발표 제목에도 민 족어 란 용어가 보인다. 민족어의 수호와 발전 (고영근, 제이앤씨, 2008)의 민족어 는 국어, 한국어, 조선어,

2014 한국어문학회 전국학술대회 통일 시대를 위한 한국 어문학의 성찰과 모색 겨나면서 민족어 란 용어가 등장하였다. 오늘의 학술대회 발표 제목에도 민 족어 란 용어가 보인다. 민족어의 수호와 발전 (고영근, 제이앤씨, 2008)의 민족어 는 국어, 한국어, 조선어, 통일 시대를 위한 북한어 연구 방향 홍 윤 표 (연세대학교) 1. 머리말 통일 시대를 위한 북한어 연구 동향 이란 주제를 발표자에게 제시한 것은 발 표자에게 통일에 대비하여 북한어를 어떻게 연구하여야 할 것인가를 제안하라는 의미일 것이다. 통일에 대비한다 는 뜻은 무엇일까? 통일을 위한 대비 보다 는 다음 단계의 대비, 즉 통일이 되었을 때를 상정하고 그때에

More information

DIY 챗봇 - LangCon

DIY 챗봇 - LangCon without Chatbot Builder & Deep Learning bage79@gmail.com Chatbot Builder (=Dialogue Manager),. We need different chatbot builders for various chatbot services. Chatbot builders can t call some external

More information

3 Gas Champion : MBB : IBM BCS PO : 2 BBc : : /45

3 Gas Champion : MBB : IBM BCS PO : 2 BBc : : /45 3 Gas Champion : MBB : IBM BCS PO : 2 BBc : : 20049 0/45 Define ~ Analyze Define VOB KBI R 250 O 2 2.2% CBR Gas Dome 1290 CTQ KCI VOC Measure Process Data USL Target LSL Mean Sample N StDev (Within) StDev

More information

<C5D8BDBAC6AEBEF0BEEEC7D02D3336C1FD2E687770>

<C5D8BDBAC6AEBEF0BEEEC7D02D3336C1FD2E687770> 텍스트언어학 36, 2014, pp. 149~177 빅데이터 적정 텍스트 추출을 위한 언어학적 접근 - 학교폭력 관련 텍스트를 중심으로- 남길임(경북대) 송현주(계명대) 이수진(경북대) Nam, Kilim, Song, Hyunju, Lee, Soojin 2014. Linguistic approach for Document Classification on Big

More information

R을 이용한 텍스트 감정분석

R을 이용한 텍스트 감정분석 R Data Analyst / ( ) / kim@mindscale.kr (kim@mindscale.kr) / ( ) ( ) Analytic Director R ( ) / / 3/45 4/45 R? 1. : / 2. : ggplot2 / Web 3. : slidify 4. : 5. Matlab / Python -> R Interactive Plots. 5/45

More information

Data Industry White Paper

Data Industry White Paper 2017 2017 Data Industry White Paper 2017 1 3 1 2 3 Interview 1 ICT 1 Recommendation System * 98 2017 Artificial 3 Neural NetworkArtificial IntelligenceAI 2 AlphaGo 1 33 Search Algorithm Deep Learning IBM

More information

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE Jul.; 29(7),

THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE Jul.; 29(7), THE JOURNAL OF KOREAN INSTITUTE OF ELECTROMAGNETIC ENGINEERING AND SCIENCE. 2018 Jul.; 29(7), 550 559. http://dx.doi.org/10.5515/kjkiees.2018.29.7.550 ISSN 1226-3133 (Print) ISSN 2288-226X (Online) Human

More information

김기남_ATDC2016_160620_[키노트].key

김기남_ATDC2016_160620_[키노트].key metatron Enterprise Big Data SKT Metatron/Big Data Big Data Big Data... metatron Ready to Enterprise Big Data Big Data Big Data Big Data?? Data Raw. CRM SCM MES TCO Data & Store & Processing Computational

More information

(JBE Vol. 23, No. 2, March 2018) (Special Paper) 23 2, (JBE Vol. 23, No. 2, March 2018) ISSN

(JBE Vol. 23, No. 2, March 2018) (Special Paper) 23 2, (JBE Vol. 23, No. 2, March 2018)   ISSN (Special Paper) 23 2, 2018 3 (JBE Vol. 23, No. 2, March 2018) https://doi.org/10.5909/jbe.2018.23.2.186 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) a), a) Robust Online Object Tracking via Convolutional

More information

(p47~53)SR

(p47~53)SR 2014.8 Semiconductor Network 47 48 Semiconductor Network 2014.8 2014.8 Semiconductor Network 49 50 Semiconductor Network 2014.8 2014.8 Semiconductor Network 51 52 Semiconductor Network 2014.8 SN 2014.8

More information

이보고서는 2010 년한국언론진흥재단의언론진흥기금을지원받아수행한것입니다. 보고서의내용은한국언론진흥재단의공식견해가아닌연구자의연구결과임을밝힙니다. 목 차 요약문 ⅳ Ⅰ. 서론 1 5 6 7 7 11 13 14 14 16 18 21 29 40-1 - 47 47 48 66 68 69 70 70 71 72 72 73 74-2 - < 표 > 목차 표 1 대한매일신보보급부수

More information

PowerPoint 프레젠테이션

PowerPoint 프레젠테이션 heecheol.seo@navercorp.com) www.chatbots.org 637 개영어챗봇 http://www.loebner.net/prizef/loebner-prize.html http://www.aisb.org.uk/media/files/loebnerprize2015/rose.pdf AIML (The Artificial Intelligence

More information

1217 WebTrafMon II

1217 WebTrafMon II (1/28) (2/28) (10 Mbps ) Video, Audio. (3/28) 10 ~ 15 ( : telnet, ftp ),, (4/28) UDP/TCP (5/28) centralized environment packet header information analysis network traffic data, capture presentation network

More information

<4D F736F F F696E74202D F ABFACB1B8C8B85FBEF0BEEEC3B3B8AEBFCDB1E2B0E8B9F8BFAAC7F6C8B228C1F6C3A2C1F829>

<4D F736F F F696E74202D F ABFACB1B8C8B85FBEF0BEEEC3B3B8AEBFCDB1E2B0E8B9F8BFAAC7F6C8B228C1F6C3A2C1F829> Ebiz 연구회 2017 9 21 정의용 FrankJeong@systrangroupcom SYSTRAN History & Technology Natural Language Processing Machine Translation History MT Technique Neural Network Neural Machine Translation Data Landscape

More information

<4D6963726F736F667420576F7264202D20C3D6BDC52049435420C0CCBDB4202D20BAB9BBE7BABB>

<4D6963726F736F667420576F7264202D20C3D6BDC52049435420C0CCBDB4202D20BAB9BBE7BABB> 최신 ICT 이슈 최신 ICT 이슈 알파고의 심층강화학습을 뒷받침한 H/W 와 S/W 환경의 진화 * 알파고의 놀라운 점은 바둑의 기본규칙조차 입력하지 않았지만 승리 방식을 스스로 알아 냈다는 것이며, 알파고의 핵심기술인 심층강화학습이 급속도로 발전한 배경에는 하드웨 어의 진화와 함께 오픈소스화를 통해 발전하는 AI 관련 소프트웨어들이 자리하고 있음 2014

More information

4 : (Hyo-Jin Cho et al.: Audio High-Band Coding based on Autoencoder with Side Information) (Special Paper) 24 3, (JBE Vol. 24, No. 3, May 2019

4 : (Hyo-Jin Cho et al.: Audio High-Band Coding based on Autoencoder with Side Information) (Special Paper) 24 3, (JBE Vol. 24, No. 3, May 2019 4 : (Hyo-Jin Cho et al.: Audio High-Band Coding based on Autoencoder with Side Information) (Special Paper) 24 3, 2019 5 (JBE Vol. 24, No. 3, May 2019) https://doi.org/10.5909/jbe.2019.24.3.387 ISSN 2287-9137

More information

_KrlGF발표자료_AI

_KrlGF발표자료_AI AI 의과거와현재그리고내일 AI is the New Electricity 2017.09.15 AI! 2 Near Future of Super Intelligence? *source l http://www.motherjones.com/media/2013/05/robots-artificial-intelligence-jobs-automation 3 4 I think

More information

<4D6963726F736F667420576F7264202D20C3D6BDC52049435420C0CCBDB4202D20BAB9BBE7BABB>

<4D6963726F736F667420576F7264202D20C3D6BDC52049435420C0CCBDB4202D20BAB9BBE7BABB> 주간기술동향 2016. 2. 24. 최신 ICT 이슈 인공지능 바둑 프로그램 경쟁, 구글이 페이스북에 리드 * 바둑은 경우의 수가 많아 컴퓨터가 인간을 넘어서기 어려움을 보여주는 사례로 꼽혀 왔 으며, 바로 그런 이유로 인공지능 개발에 매진하는 구글과 페이스북은 바둑 프로그램 개 발 경쟁을 벌여 왔으며, 프로 9 단에 도전장을 낸 구글이 일단 한발 앞서 가는

More information

歯15-ROMPLD.PDF

歯15-ROMPLD.PDF MSI & PLD MSI (Medium Scale Integrate Circuit) gate adder, subtractor, comparator, decoder, encoder, multiplexer, demultiplexer, ROM, PLA PLD (programmable logic device) fuse( ) array IC AND OR array sum

More information

(JBE Vol. 24, No. 2, March 2019) (Special Paper) 24 2, (JBE Vol. 24, No. 2, March 2019) ISSN

(JBE Vol. 24, No. 2, March 2019) (Special Paper) 24 2, (JBE Vol. 24, No. 2, March 2019)   ISSN (Special Paper) 24 2, 2019 3 (JBE Vol. 24, No. 2, March 2019) https://doi.org/10.5909/jbe.2019.24.2.234 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) SIFT a), a), a), a) SIFT Image Feature Extraction

More information

2 : (Seungsoo Lee et al.: Generating a Reflectance Image from a Low-Light Image Using Convolutional Neural Network) (Regular Paper) 24 4, (JBE

2 : (Seungsoo Lee et al.: Generating a Reflectance Image from a Low-Light Image Using Convolutional Neural Network) (Regular Paper) 24 4, (JBE 2: (Seungsoo Lee et al.: Generating a Reflectance Image from a Low-Light Image Using Convolutional Neural Network) (Regular Paper) 24 4, 2019 7 (JBE Vol. 24, No. 4, July 2019) https://doi.org/10.5909/jbe.2019.24.4.623

More information

PowerPoint 프레젠테이션

PowerPoint 프레젠테이션 1 2 3 3-1 3-2 3-3 Large-scale data 개요기계학습기반자료분석기술교통분석에기계학습적용사례 1 CNN 을활용한대중교통수요예측 2 RNN 을활용한공로통행속도예측 3 DQN 을이용한최적교통신호제어 4 시연 Large-Scale Data 기술요소 전수자료 이력자료누적 ( 자료를지우지않음 ) Hadoop HDFS MapReduce 병렬 DBMS

More information

종합설계 I (Xcode and Source Control )

종합설계 I  (Xcode and Source Control ) Sogang University: Dept of Computer Science 구명완교수 서강대학교컴퓨터공학과 Email: mwkoo9@gmail.com 내용 개념도 시맨틱해석기 대화상태추적기 대화관리기 자연언어생성기 결론 개념도 음성인식 음성대화 음성대화솔류션사례 음성대화서비스 음성대화로봇 Apple Siri Google MS Cortana Amazon Echo

More information

..........(......).hwp

..........(......).hwp START START 질문을 통해 우선순위를 결정 의사결정자가 질문에 답함 모형데이터 입력 목표계획법 자료 목표계획법 모형에 의한 해의 도출과 득실/확률 분석 END 목표계획법 산출결과 결과를 의사 결정자에게 제공 의사결정자가 결과를 검토하여 만족여부를 대답 의사결정자에게 만족하는가? Yes END No 목표계획법 수정 자료 개선을 위한 선택의 여지가 있는지

More information

Microsoft PowerPoint - 실습소개와 AI_ML_DL_배포용.pptx

Microsoft PowerPoint - 실습소개와 AI_ML_DL_배포용.pptx 실습강의개요와인공지능, 기계학습, 신경망 < 인공지능입문 > 강의 허민오 Biointelligence Laboratory School of Computer Science and Engineering Seoul National University 실습강의개요 노트북을꼭지참해야하는강좌 신경망소개 (2 주, 허민오 ) Python ( 프로그래밍언어 ) (2주, 김준호

More information

歯경영혁신 단계별 프로그램 사례.ppt

歯경영혁신 단계별 프로그램 사례.ppt BMS Infra BMS Location A B C D D A Location Card + Location SET Card : 1 : : Location Card ( ) ( Over ) Location Card Card Location Card ( ) ( ) Location Card LocationCard RACK1 AGE / 7 ( ) SET Location

More information

기술 Roadmap

기술 Roadmap Deep Learning 기술의 Commerce 적용사례 2016. 12. 2. SK planet Machine Intelligence Lab. 전병기 1. SK플래닛소개 2. Deep Learning의가능성 3. 모바일신용카드인식기술 4. 자동번역기술 5. 패션이미지검색기술 6. 맺음말 SK planet 2 SK planet 3 SK planet 4 SK

More information

DW 개요.PDF

DW 개요.PDF Data Warehouse Hammersoftkorea BI Group / DW / 1960 1970 1980 1990 2000 Automating Informating Source : Kelly, The Data Warehousing : The Route to Mass Customization, 1996. -,, Data .,.., /. ...,.,,,.

More information

정보기술응용학회 발표

정보기술응용학회 발표 , hsh@bhknuackr, trademark21@koreacom 1370, +82-53-950-5440 - 476 - :,, VOC,, CBML - Abstract -,, VOC VOC VOC - 477 - - 478 - Cost- Center [2] VOC VOC, ( ) VOC - 479 - IT [7] Knowledge / Information Management

More information

PowerPoint Presentation

PowerPoint Presentation Dependency Parser 자연언어처리 Probabilistic CFG (PCFG) - CFG - PCFG with saw with saw astronomers ears saw stars telescope astronomers ears saw stars telescope PCFG example Repeated work Parsing PCFG: CKY CKY

More information

01 AI Definition 02 Deep Learning Theory - Linear Regression - Cost Function - Gradient Descendent - Logistic Regression - Activation Function - Conce

01 AI Definition 02 Deep Learning Theory - Linear Regression - Cost Function - Gradient Descendent - Logistic Regression - Activation Function - Conce Artificial Intelligence for Deep Learning 01 AI Definition 02 Deep Learning Theory - Linear Regression - Cost Function - Gradient Descendent - Logistic Regression - Activation Function - Concept of Neural

More information

- iii - - i - - ii - - iii - 국문요약 종합병원남자간호사가지각하는조직공정성 사회정체성과 조직시민행동과의관계 - iv - - v - - 1 - - 2 - - 3 - - 4 - - 5 - - 6 - - 7 - - 8 - - 9 - - 10 - - 11 - - 12 - - 13 - - 14 - α α α α - 15 - α α α α α α

More information

저작자표시 - 비영리 - 변경금지 2.0 대한민국 이용자는아래의조건을따르는경우에한하여자유롭게 이저작물을복제, 배포, 전송, 전시, 공연및방송할수있습니다. 다음과같은조건을따라야합니다 : 저작자표시. 귀하는원저작자를표시하여야합니다. 비영리. 귀하는이저작물을영리목적으로이용할

저작자표시 - 비영리 - 변경금지 2.0 대한민국 이용자는아래의조건을따르는경우에한하여자유롭게 이저작물을복제, 배포, 전송, 전시, 공연및방송할수있습니다. 다음과같은조건을따라야합니다 : 저작자표시. 귀하는원저작자를표시하여야합니다. 비영리. 귀하는이저작물을영리목적으로이용할 저작자표시 - 비영리 - 변경금지 2.0 대한민국 이용자는아래의조건을따르는경우에한하여자유롭게 이저작물을복제, 배포, 전송, 전시, 공연및방송할수있습니다. 다음과같은조건을따라야합니다 : 저작자표시. 귀하는원저작자를표시하여야합니다. 비영리. 귀하는이저작물을영리목적으로이용할수없습니다. 변경금지. 귀하는이저작물을개작, 변형또는가공할수없습니다. 귀하는, 이저작물의재이용이나배포의경우,

More information

Vol.259 C O N T E N T S M O N T H L Y P U B L I C F I N A N C E F O R U M

Vol.259 C O N T E N T S M O N T H L Y P U B L I C F I N A N C E F O R U M 2018.01 Vol.259 C O N T E N T S 02 06 28 61 69 99 104 120 M O N T H L Y P U B L I C F I N A N C E F O R U M 2 2018.1 3 4 2018.1 1) 2) 6 2018.1 3) 4) 7 5) 6) 7) 8) 8 2018.1 9 10 2018.1 11 2003.08 2005.08

More information

Oracle Apps Day_SEM

Oracle Apps Day_SEM Senior Consultant Application Sales Consulting Oracle Korea - 1. S = (P + R) x E S= P= R= E= Source : Strategy Execution, By Daniel M. Beall 2001 1. Strategy Formulation Sound Flawed Missed Opportunity

More information

SRC PLUS 제어기 MANUAL

SRC PLUS 제어기 MANUAL ,,,, DE FIN E I N T R E A L L O C E N D SU B E N D S U B M O TIO

More information

Manufacturing6

Manufacturing6 σ6 Six Sigma, it makes Better & Competitive - - 200138 : KOREA SiGMA MANAGEMENT C G Page 2 Function Method Measurement ( / Input Input : Man / Machine Man Machine Machine Man / Measurement Man Measurement

More information

. "" "",.... :...,,....,.. :..,,,..,,...,.... 2

.  ,.... :...,,....,.. :..,,,..,,...,.... 2 RD-5405 /.. . "" "",.... :...,,....,.. :..,,,..,,...,.... 2 ..,,..,.. (,,,, )......,...,., ( ),,,,.,. (, )..,...... BD/DVD CD TV, VCR,........ (+, -).,,..... 3 ... 2... 3....3... 5... 9... 10...11...11...

More information

(Exposure) Exposure (Exposure Assesment) EMF Unknown to mechanism Health Effect (Effect) Unknown to mechanism Behavior pattern (Micro- Environment) Re

(Exposure) Exposure (Exposure Assesment) EMF Unknown to mechanism Health Effect (Effect) Unknown to mechanism Behavior pattern (Micro- Environment) Re EMF Health Effect 2003 10 20 21-29 2-10 - - ( ) area spot measurement - - 1 (Exposure) Exposure (Exposure Assesment) EMF Unknown to mechanism Health Effect (Effect) Unknown to mechanism Behavior pattern

More information

목 차 Ⅰ. 정보기술의 환경 변화 Ⅱ. 차량-IT Convergence Ⅲ. 차량 센서 연계 서비스 Ⅳ. 차량-IT 융합 발전방향

목 차 Ⅰ. 정보기술의 환경 변화 Ⅱ. 차량-IT Convergence Ⅲ. 차량 센서 연계 서비스 Ⅳ. 차량-IT 융합 발전방향 차량-IT 융합 기반의 미래형 서비스 발전 동향 이범태 (현대자동차) 목 차 Ⅰ. 정보기술의 환경 변화 Ⅱ. 차량-IT Convergence Ⅲ. 차량 센서 연계 서비스 Ⅳ. 차량-IT 융합 발전방향 Ⅰ. 정보 기술의 환경변화 1. 정보기술의 발전 2. 자동차 전장 시스템의 발전 1. 정보기술의 발전 정보기술은 통신 네트워크의 급속한 발전, 단말의 고기능화,

More information

Visual recognition in the real world SKT services

Visual recognition  in the real world SKT services Visual recognition in the real world SKT services 박병관 SK Telecom AI Center / 영상인식기술 Cell 2019.07.02 SKT Services 2 Contents 1. T map 도로교통정보인식 a. 서비스개요 b. Core Engine Architecture c. Core Engine d. Multi

More information

2 : (EunJu Lee et al.: Speed-limit Sign Recognition Using Convolutional Neural Network Based on Random Forest). (Advanced Driver Assistant System, ADA

2 : (EunJu Lee et al.: Speed-limit Sign Recognition Using Convolutional Neural Network Based on Random Forest). (Advanced Driver Assistant System, ADA (JBE Vol. 20, No. 6, November 2015) (Regular Paper) 20 6, 2015 11 (JBE Vol. 20, No. 6, November 2015) http://dx.doi.org/10.5909/jbe.2015.20.6.938 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) a), a),

More information

歯49손욱.PDF

歯49손욱.PDF 2002 14 C Inventory An Estimation of 14 C Inventory on Each Unit of Wolsong NPP,,, 103-16 14 C 14 C Inventory 14 C Inventory 14 C 14 C, [Inventory] = [ 14 C ] - [ 14 C ] 14 C 14 C 13 C, 14 N 17 O [ 13

More information

PowerPoint Presentation

PowerPoint Presentation 기계학습을통한 시계열데이터분석및 금융시장예측응용 울산과학기술원 전기전자컴퓨터공학부최재식 얼굴인식 Facebook 의얼굴인식기 (DeepFace) 가사람과비슷한인식성능을보임 문제 : 사진에서연애인의이름을맞추기 사람의인식율 : 97.5% vs DeepFace 의인식률 : 97.35% (2014 년 3 월 ) 물체인식 ImageNet (http://image-net.org):

More information

Pattern Recognition

Pattern Recognition 딥러닝이해및미디어응용 아주대학교구형일 인공지능 / 기계학습 / 딥러닝 AI 에관한 4 개의관점 Humanly Rationally Thinking Thinking Humanly Thinking Rationally Acting Acting Humanly Acting Rationally Acting Humanly 사람처럼일하는 / 행동하는기계 인공지능은사람에의해서수행될때지능이필요한일을수행하는기계를만드는기술이다.

More information

아버지의 이름으로 고 정성철 소방령 자녀 예술경영전공 정비담 씨 소방공무원 국가직 촉구 1인 시위 지난 9월 27일 한 청년이 돌아가신 아버지의 정복을 입고 서울 광화문광 장에서 1인 시위를 벌였다. 이 청년은 지난 7월 광주에서 헬기 추락 사고로 순직한 고 정성철 소

아버지의 이름으로 고 정성철 소방령 자녀 예술경영전공 정비담 씨 소방공무원 국가직 촉구 1인 시위 지난 9월 27일 한 청년이 돌아가신 아버지의 정복을 입고 서울 광화문광 장에서 1인 시위를 벌였다. 이 청년은 지난 7월 광주에서 헬기 추락 사고로 순직한 고 정성철 소 2014.10.13 제239호 2면: 아버지의 이름으로 3면: 반복되는 입시와 수업권 침해 논란 4면: 신자유주의적 대학 개혁과 한예종 5면: 중앙일보 대학평가 논란 6면: 최정화 개인전 «총,천연색» 리뷰 7면: 현대음악, 아르스노바 8면: 세운상가 개방회로 인터뷰 9면: 그랜드 민트 페스티벌 10면: 빅데이터와 영상 11면: «제국의 위안부» 리뷰 12면:

More information

歯RCM

歯RCM Reliability Centered Maintenance Page 2 1.,,,. Mode Component, Sub-system, System, System. Reliability Centered Maintenance :, program? Mechanism Page 3 Page 4. Mode Mode () () (FMEA) (FTA) (LTA) System

More information

Network seminar.key

Network seminar.key Intro to Network .. 2 4 ( ) ( ). ?!? ~! This is ~ ( ) /,,,???? TCP/IP Application Layer Transfer Layer Internet Layer Data Link Layer Physical Layer OSI 7 TCP/IP Application Layer Transfer Layer 3 4 Network

More information

YSU_App_2.0-2

YSU_App_2.0-2 Application System 2. 0 Youngsan University Identity Graphic Standards Stationery Business Card Business Card Letterhead-Korean Letterhead-English Envelope_Korean Envelope_English Envelope_Window Envelope_Large

More information

SOSCON-MXNET_1014

SOSCON-MXNET_1014 딥러닝계의블루오션, Apache MXNet 공헌하기 윤석찬, Amazon Web Services 오규삼, 삼성 SDS SAMSUNG OPEN SOURCE CONFERENCE 018 목차 11 1 : 4 2 031 1 1 21 51: 1 L 1 S D A 1 S D N M Deep Learning 101 SAMSUNG OPEN SOURCE CONFERENCE

More information

April 2014 BROWN Education Webzine vol.2 생명을 꿈꾸다 목차 From Editor 아침에는 다리가 4개,점심에는 2개, 저녁에는 3개인 것은? Guidance 익숙해지는 일상 속에서 우리아이 자립심 키우기 환경을 지키는 아이들의 좋은 습

April 2014 BROWN Education Webzine vol.2 생명을 꿈꾸다 목차 From Editor 아침에는 다리가 4개,점심에는 2개, 저녁에는 3개인 것은? Guidance 익숙해지는 일상 속에서 우리아이 자립심 키우기 환경을 지키는 아이들의 좋은 습 April 2014 BROWN Education Webzine vol.2 BROWN MAGAZINE Webzine vol.2 April 2014 BROWN Education Webzine vol.2 생명을 꿈꾸다 목차 From Editor 아침에는 다리가 4개,점심에는 2개, 저녁에는 3개인 것은? Guidance 익숙해지는 일상 속에서 우리아이 자립심 키우기

More information

방송공학회논문지 제18권 제2호

방송공학회논문지 제18권 제2호 방송공학회논문지 제 20권 6호 (2015년 11월) 특집논문 : 2015년 하계학술대회 좌장추천 우수논문 프레넬 회절을 이용한 디지털 홀로그램 암호화 알고리즘 새로운 광적응 효과 모델을 이용한 정교한 영상 화질 측정 민방위 경보 방송에 대한 정보 수용자 인식 연구 UHDTV 방송을 위한 공간 변조 다중 안테나 시스템 수신 성능 분석 홍보동영상 제작 서비스를

More information

#SPS/C-5050.B.

#SPS/C-5050.B. PARTS BOOK SPS/C-5050 Series SPS/C-8050 Series Purposes H : Heavy material This is a parts book. It cannot be used as a manual. CONTENTS A BC D EF G HI J K L M N O P Q R ST U V W X Y Z Machine Body Mechanism

More information

example code are examined in this stage The low pressure pressurizer reactor trip module of the Plant Protection System was programmed as subject for

example code are examined in this stage The low pressure pressurizer reactor trip module of the Plant Protection System was programmed as subject for 2003 Development of the Software Generation Method using Model Driven Software Engineering Tool,,,,, Hoon-Seon Chang, Jae-Cheon Jung, Jae-Hack Kim Hee-Hwan Han, Do-Yeon Kim, Young-Woo Chang Wang Sik, Moon

More information

(JBE Vol. 23, No. 2, March 2018) (Special Paper) 23 2, (JBE Vol. 23, No. 2, March 2018) ISSN

(JBE Vol. 23, No. 2, March 2018) (Special Paper) 23 2, (JBE Vol. 23, No. 2, March 2018)   ISSN (Special Paper) 23 2, 2018 3 (JBE Vol. 23, No. 2, March 2018) https://doi.org/10.5909/jbe.2018.23.2.246 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) CNN a), a), a) CNN-Based Hand Gesture Recognition

More information

Vertical Probe Card Technology Pin Technology 1) Probe Pin Testable Pitch:03 (Matrix) Minimum Pin Length:2.67 High Speed Test Application:Test Socket

Vertical Probe Card Technology Pin Technology 1) Probe Pin Testable Pitch:03 (Matrix) Minimum Pin Length:2.67 High Speed Test Application:Test Socket Vertical Probe Card for Wafer Test Vertical Probe Card Technology Pin Technology 1) Probe Pin Testable Pitch:03 (Matrix) Minimum Pin Length:2.67 High Speed Test Application:Test Socket Life Time: 500000

More information

Page 2 of 6 Here are the rules for conjugating Whether (or not) and If when using a Descriptive Verb. The only difference here from Action Verbs is wh

Page 2 of 6 Here are the rules for conjugating Whether (or not) and If when using a Descriptive Verb. The only difference here from Action Verbs is wh Page 1 of 6 Learn Korean Ep. 13: Whether (or not) and If Let s go over how to say Whether and If. An example in English would be I don t know whether he ll be there, or I don t know if he ll be there.

More information

SchoolNet튜토리얼.PDF

SchoolNet튜토리얼.PDF Interoperability :,, Reusability: : Manageability : Accessibility :, LMS Durability : (Specifications), AICC (Aviation Industry CBT Committee) : 1988, /, LMS IMS : 1997EduCom NLII,,,,, ARIADNE (Alliance

More information

............ ......

............ ...... 3 N.P 하모닉드라이브 의 작동원리 서큘러스플라인 웨이브제네레이터 플렉스플라인 플렉스플라인은 웨이브제네레 이터에 의해 타원형상으로 탄 성변형되어 이로인해 타원의 장축부분에서는 서큘러스플라 인과 이가 맞물리고 단축부분 에서는 이가 완전히 떨어진 상태로

More information

PowerPoint 프레젠테이션

PowerPoint 프레젠테이션 I. 문서표준 1. 문서일반 (HY중고딕 11pt) 1-1. 파일명명체계 1-2. 문서등록정보 2. 표지표준 3. 개정이력표준 4. 목차표준 4-1. 목차슬라이드구성 4-2. 간지슬라이드구성 5. 일반표준 5-1. 번호매기기구성 5-2. 텍스트박스구성 5-3. 테이블구성 5-4. 칼라테이블구성 6. 적용예제 Machine Learning Credit Scoring

More information

(JBE Vol. 22, No. 2, March 2017) (Special Paper) 22 2, (JBE Vol. 22, No. 2, March 2017) ISSN

(JBE Vol. 22, No. 2, March 2017) (Special Paper) 22 2, (JBE Vol. 22, No. 2, March 2017)   ISSN (Special Paper) 22 2, 2017 3 (JBE Vol. 22, No. 2, March 2017) https://doi.org/10.5909/jbe.2017.22.2.162 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) Convolutional Neural Network a), b), a), a), Facial

More information

IPAK 윤리강령 나는 _ 한국IT전문가협회 회원으로서 긍지와 보람을 느끼며 정보시스템 활용하 자. 나는 _동료, 단체 및 국가 나아가 인류사회에 대하여 철저한 책임 의식을 가진 다. 나는 _ 활용자에 대하여 그 편익을 증진시키는데 최선을 다한다. 나는 _ 동료에 대해

IPAK 윤리강령 나는 _ 한국IT전문가협회 회원으로서 긍지와 보람을 느끼며 정보시스템 활용하 자. 나는 _동료, 단체 및 국가 나아가 인류사회에 대하여 철저한 책임 의식을 가진 다. 나는 _ 활용자에 대하여 그 편익을 증진시키는데 최선을 다한다. 나는 _ 동료에 대해 IPAK 윤리강령 나는 _ 한국IT전문가협회 회원으로서 긍지와 보람을 느끼며 정보시스템 활용하 자. 나는 _동료, 단체 및 국가 나아가 인류사회에 대하여 철저한 책임 의식을 가진 다. 나는 _ 활용자에 대하여 그 편익을 증진시키는데 최선을 다한다. 나는 _ 동료에 대해서 도의와 성실과 지식을 바탕으로 서로 우애하고 경애한다. 나는 _ 단체와 국가에 대해서 그

More information

6주차.key

6주차.key 6, Process concept A program in execution Program code PCB (process control block) Program counter, registers, etc. Stack Heap Data section => global variable Process in memory Process state New Running

More information

OPCTalk for Hitachi Ethernet 1 2. Path. DCOMwindow NT/2000 network server. Winsock update win95. . . 3 Excel CSV. Update Background Thread Client Command Queue Size Client Dynamic Scan Block Block

More information

[White Paper]다시보는 시맨틱 웹 그리고 시맨틱 기술 하는 Tabulator와 Sindice에 기반한 데이터 매쉬업 및 브라우징 서비스인 sig.ma는 꼭 한번 경험해 봐야 할 대상이 다. 또한, SemaPlorer나 DBpedia Mobile 경우는 LOD

[White Paper]다시보는 시맨틱 웹 그리고 시맨틱 기술 하는 Tabulator와 Sindice에 기반한 데이터 매쉬업 및 브라우징 서비스인 sig.ma는 꼭 한번 경험해 봐야 할 대상이 다. 또한, SemaPlorer나 DBpedia Mobile 경우는 LOD [White Paper]다시보는 시맨틱 웹 그리고 시맨틱 기술 그림 6. Wikipedia의 Korea inforbox와 dbpedia.org의 Korea 데이터 sheet 진정한 성공을 원한다면, 머리는 구름 위에 있어도 그 발은 땅을 굳게 디디고 있어야 한단다. 시맨틱 웹의 비전이 나 LOD의 발전은 분명 미래에 대한 수 많은 가능성을 제시하고 있다. 하지만,

More information

슬라이드 1

슬라이드 1 4. Mobile Service Technology Mobile Computing Lecture 2012. 10. 5 안병익 (biahn99@gmail.com) 강의블로그 : Mobilecom.tistory.com 2 Mobile Service in Korea 3 Mobile Service Mobility 4 Mobile Service in Korea 5 Mobile

More information

/ TV 80 () DAB 2001 2002 2003 2004 2005 2010 Analog/Digital CATV Services EPG TV ( 60 ) TV ( Basic, Tier, Premiums 60 ) VOD Services Movies In Demand ( 20 ) Education N- VOD (24 ) Digital Music

More information

Preliminary spec(K93,K62_Chip_081118).xls

Preliminary spec(K93,K62_Chip_081118).xls 2.4GHz Antenna K93- Series KMA93A2450X-M01 Antenna mulilayer Preliminary Spec. Features LTCC Based designs Monolithic SMD with small, low-profile and light-weight type Wide bandwidth Size : 9 x 3 x 1.0mm

More information

02본문

02본문 46 특집 : 딥러닝기반방송미디어기술 특집 딥러닝기반방송미디어기술 딥러닝기반의음성 / 오디오기술 Speech/Audio Processing based on Deep Learning 이영한 / KETI Ⅰ. 서론 인간의두뇌를모델링하는뉴럴네트워크연구는 1940 년대신경세포의모델링부터시작하여현재까지다양한기술이축적되어왔다. 특히 backpropagation 이제안된이후에

More information

(3) () () LOSS LOSS LOSS LOSS (4) = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100

(3) () () LOSS LOSS LOSS LOSS (4) = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100 1.,.. 2. (1) Flow + ( ) (2) Flow Flow (LINE) ) (LINE) ModelC/T LOSS DAT A Check Sheet ((%) (T PM) (LOSS) - (3) () () LOSS LOSS LOSS LOSS (4) = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100 = 100

More information

Model Investor MANDO Portal Site People Customer BIS Supplier C R M PLM ERP MES HRIS S C M KMS Web -Based

Model Investor MANDO Portal Site People Customer BIS Supplier C R M PLM ERP MES HRIS S C M KMS Web -Based e- Business Web Site 2002. 04.26 Model Investor MANDO Portal Site People Customer BIS Supplier C R M PLM ERP MES HRIS S C M KMS Web -Based Approach High E-Business Functionality Web Web --based based KMS/BIS

More information

untitled

untitled Huvitz Digital Microscope HDS-5800 Dimensions unit : mm Huvitz Digital Microscope HDS-5800 HDS-MC HDS-SS50 HDS-TS50 SUPERIORITY Smart Optical Solutions for You! Huvitz Digital Microscope HDS-5800 Contents

More information

PowerPoint Presentation

PowerPoint Presentation 철도궤도결함탐지를위한영역기반및픽셀기반딥러닝기법적용사례 Detection of track defects by region- and pixel-based deep learning approaches 한국철도기술연구원 / 첨단궤도토목본부황성호선임연구원 2015 The MathWorks, Inc. 1 목차 1. 회사및발표자소개 2. 철도및궤도소개 3. 프로젝트개요

More information

저작자표시 - 비영리 - 변경금지 2.0 대한민국 이용자는아래의조건을따르는경우에한하여자유롭게 이저작물을복제, 배포, 전송, 전시, 공연및방송할수있습니다. 다음과같은조건을따라야합니다 : 저작자표시. 귀하는원저작자를표시하여야합니다. 비영리. 귀하는이저작물을영리목적으로이용할

저작자표시 - 비영리 - 변경금지 2.0 대한민국 이용자는아래의조건을따르는경우에한하여자유롭게 이저작물을복제, 배포, 전송, 전시, 공연및방송할수있습니다. 다음과같은조건을따라야합니다 : 저작자표시. 귀하는원저작자를표시하여야합니다. 비영리. 귀하는이저작물을영리목적으로이용할 저작자표시 - 비영리 - 변경금지 2.0 대한민국 이용자는아래의조건을따르는경우에한하여자유롭게 이저작물을복제, 배포, 전송, 전시, 공연및방송할수있습니다. 다음과같은조건을따라야합니다 : 저작자표시. 귀하는원저작자를표시하여야합니다. 비영리. 귀하는이저작물을영리목적으로이용할수없습니다. 변경금지. 귀하는이저작물을개작, 변형또는가공할수없습니다. 귀하는, 이저작물의재이용이나배포의경우,

More information

Microsoft PowerPoint - WiseNLU(ETRI, 임수종) 배포본

Microsoft PowerPoint - WiseNLU(ETRI, 임수종) 배포본 WiseNLU: 지식처리를 위한 자연어 의미 이해 기술 2015. 8. 21. 임수종/이충희/임준호/김현기 ETRI 지식마이닝연구실 1/69 1/63 과제개념 : WiseQA 복잡한자연어로기술된문제의의미를이해하고정답을추론하여생성함 자연어질문 연구목표 자연어질의응답 문제이해정답후보추론최적정답생성 정답, 근거, 정확도 휴먼피드백 자연어어휘 / 문장 / 문맥간의미이해기술개발

More information

1. 연구 개요 q 2013년 연구목표 제2-1과제명 건축물의 건강친화형 관리 및 구법 기술 연구목표 건강건축 수명예측 Lifecycle Health Assessment (LHA) 모델 개발 건축물의 비용 기반 분석기술(Cost-based Lifecycle Health

1. 연구 개요 q 2013년 연구목표 제2-1과제명 건축물의 건강친화형 관리 및 구법 기술 연구목표 건강건축 수명예측 Lifecycle Health Assessment (LHA) 모델 개발 건축물의 비용 기반 분석기술(Cost-based Lifecycle Health 지속가능 건강건축을 위한 비용기반 LHA 모델 2013. 11. 15-16 목 차 1. 연구 개요 2. Cost-based LHA 모델의 개념 3. Cost-based LHA 모델의 운용 4. 결론 2 283 1. 연구 개요 q 2013년 연구목표 제2-1과제명 건축물의 건강친화형 관리 및 구법 기술 연구목표 건강건축 수명예측 Lifecycle Health

More information

ÀÎÅͳÝ-°ø°£µµÇüÇØ

ÀÎÅͳÝ-°ø°£µµÇüÇØ .. Q.... M M : M Q : Q M : //Q.,.. I FG FE F FG, HG EH H HG F G FG ;!;_F _FG ;!;_G _F ;!;_'_;!; F F... 5. 5. 6. 5 7. 0 8. 7 9. ' FG, HG H G, H F E G H '. FG HG F, H. FH ' FH ' ' {} +{} -(') cos h -;!;

More information

첨 부 1. 설문분석 결과 2. 교육과정 프로파일 169

첨 부 1. 설문분석 결과 2. 교육과정 프로파일 169 첨부 168 첨 부 1. 설문분석 결과 2. 교육과정 프로파일 169 Ⅰ-1. 설문조사 개요 Ⅰ. 설문분석 결과 병무청 직원들이 생각하는 조직문화, 교육에 대한 인식, 역량 중요도/수행도 조사를 인터넷을 통해 실 시 총 1297명의 응답을 받았음 (95% 신뢰수준에 표본오차는 ±5%). 조사 방법 인터넷 조사 조사 기간 2005년 5월 4일 (목) ~ 5월

More information

04서종철fig.6(121~131)ok

04서종철fig.6(121~131)ok Development of Mobile Applications Applying Digital Storytelling About Ecotourism Resources Seo, Jongcheol* Lee, Seungju**,,,. (mobile AIR)., 3D.,,.,.,,, Abstract : In line with fast settling trend of

More information

15_3oracle

15_3oracle Principal Consultant Corporate Management Team ( Oracle HRMS ) Agenda 1. Oracle Overview 2. HR Transformation 3. Oracle HRMS Initiatives 4. Oracle HRMS Model 5. Oracle HRMS System 6. Business Benefit 7.

More information

슬라이드 제목 없음

슬라이드 제목 없음 (JTC1/SC6) sjkoh@knu.ac.kr JTC1 JTC1/SC6/WG7 ECTP/RMCP/MMC (JTC1/SC6) 2/48 JTC1 ISO/IEC JTC1 Joint Technical Committee 1 ( ) ISO/TC 97 ( ) IEC/TC 83 ( ) Information Technology (IT) http://www.jtc1.org

More information

<4D F736F F D20B1E2C8B9BDC3B8AEC1EE2DB0FBB3EBC1D8>

<4D F736F F D20B1E2C8B9BDC3B8AEC1EE2DB0FBB3EBC1D8> 딥러닝기술동향 - CNN 과 RNN 을중심으로 - 곽노준박성헌 * 김대식 * 서울대학교교수서울대학교박사과정 * 본고에서는딥러닝의여러가지분야중최근영상인식분야에서기존방법들보다월등한성능을보이고있는컨볼루션신경망 (Convolutional Neural Networks: CNN) 과음성인식이나자연어처리등에적용되어뛰어난성능을보이는순환신경망 (Recurrent Neural

More information

마음_2012._2월_진하게LLkk-777 - 복사본.hwp

마음_2012._2월_진하게LLkk-777 - 복사본.hwp 마 음 바다는 웅장하다. 넓은 바다가 아무리 둘러보아도 귀퉁이가 없다. 하늘과 맞닿은 수 평선이 나타난다. 어둠을 서서히 뚫고 일어서는 거대한 용솟음이 이어진다. 철렁철렁, 넘실 넘실 거리는 파도는 새벽의 햇볕을 굽이굽이 반짝거리게 한다. 붉은 덩어리가 야금야금 제 모습을 나타낸다. 수평선의 직선이 둥그런 곡선으로 바뀌는 듯이 동그랗게 올라오는 신비의 물체에

More information

<C1DF3320BCF6BEF7B0E8C8B9BCAD2E687770>

<C1DF3320BCF6BEF7B0E8C8B9BCAD2E687770> 2012학년도 2학기 중등과정 3학년 국어 수업 계획서 담당교사 - 봄봄 현영미 / 시온 송명근 1. 학습 목적 말씀으로 천지를 창조하신 하나님이 당신의 형상대로 지음 받은 우리에게 언어를 주셨고, 그 말씀의 능 력이 우리의 언어생활에도 나타남을 깨닫고, 그 능력을 기억하여 표현하고 이해함으로 아름다운 언어생활 을 누릴 뿐만 아니라 언어문화 창조에 이바지함으로써

More information

À±½Â¿í Ãâ·Â

À±½Â¿í Ãâ·Â Representation, Encoding and Intermediate View Interpolation Methods for Multi-view Video Using Layered Depth Images The multi-view video is a collection of multiple videos, capturing the same scene at

More information

4 : CNN (Sangwon Suh et al.: Dual CNN Structured Sound Event Detection Algorithm Based on Real Life Acoustic Dataset) (Regular Paper) 23 6, (J

4 : CNN (Sangwon Suh et al.: Dual CNN Structured Sound Event Detection Algorithm Based on Real Life Acoustic Dataset) (Regular Paper) 23 6, (J (Regular Paper) 23 6, 2018 11 (JBE Vol. 23, No. 6, November 2018) https://doi.org/10.5909/jbe.2018.23.6.855 ISSN 2287-9137 (Online) ISSN 1226-7953 (Print) CNN a), a), a), a), a) Dual CNN Structured Sound

More information

e hwp

e hwp TITLE 'Dew Pressure Calculation for the Condenser Pressure' IN-UNITS ENG DEF-STREAMS CONVEN ALL DESCRIPTION " General Simulation with English Units : F, psi, lb/hr, lbmol/hr, Btu/hr, cuft/hr. Property

More information

2 : CNN (Jaeyoung Kim et al.: Experimental Comparison of CNN-based Steganalysis Methods with Structural Differences) (Regular Paper) 24 2, (JBE

2 : CNN (Jaeyoung Kim et al.: Experimental Comparison of CNN-based Steganalysis Methods with Structural Differences) (Regular Paper) 24 2, (JBE 2: CNN (Jaeyoung Kim et al.: Experimental Comparison of CNN-based Steganalysis Methods with Structural Differences) (Regular Paper) 24 2, 2019 3 (JBE Vol. 24, No. 2, March 2019) https://doi.org/10.5909/jbe.2019.24.2.315

More information