Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Graph Convolutional Neural Networks

3,392 views

Published on

Graph Convolutional Deep Learning seminar of smart bean forum at Naver D2 Startup Factory Lounge 2019-03-07. speaker : Shin-Dong Kang

Published in: Data & Analytics
  • My personal experience with research paper writing services was highly positive. I sent a request to ⇒ www.HelpWriting.net ⇐ and found a writer within a few minutes. Because I had to move house and I literally didn’t have any time to sit on a computer for many hours every evening. Thankfully, the writer I chose followed my instructions to the letter. I know we can all write essays ourselves. For those in the same situation I was in, I recommend ⇒ www.HelpWriting.net ⇐.
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here
  • My friend sent me a link to to tis site. This awesome company. They wrote my entire research paper for me, and it turned out brilliantly. I highly recommend this service to anyone in my shoes. ⇒ www.HelpWriting.net ⇐.
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here
  • Get the best essay, research papers or dissertations. from ⇒ www.WritePaper.info ⇐ A team of professional authors with huge experience will give u a result that will overcome your expectations.
       Reply 
    Are you sure you want to  Yes  No
    Your message goes here

Graph Convolutional Neural Networks

  1. 1. Graph Convolutional Neural Networks 강신동 smart bean forum leader (주)지능도시 CEO ceo@idosi.com 2019-03-07 Smart Bean forum seminar at Naver D2 Startup Factory Lounge 1
  2. 2. Smart Bean forum 2 Facebook Group http://facebook.com/groups/smartbean2 - AI, Deep Learning etc - Industrial Market Tech Biz Cooperation - Smart City - IoT - Smart Factory - Smart City
  3. 3. Speaker 3 강신동 (Shin-Dong Kang) - smart bean forum leader - (주)지능도시 CEO - ceo@idosi.com - www.idosi.com - Deep Learning Tech Solution Provider - Deep Learning 용역 (연구,개발)
  4. 4. Deep Learning of Neural Networks 4
  5. 5. Machine Learning, Deep Learning 접근법 5 - 기존 방식 1. 전문 지식 기반 2. 수학적 모델링 3. 입력값 입력 4. 예측 결과 출력 - 딥러닝 방식 1. 입력값과 출력값의 측정 데이터 수집 2. 수집된 출력값의 오차 줄이도록 학습 3. 모델링 자동 완성 4. 미지의 입력값 입력 5. 예측 결과 출력 Data set is the source code !
  6. 6. AlphaGo 6
  7. 7. AlphaFold 7 Google DeepMind 과학, 생명공학, 의학, 의약 산업 아미노산 1차원 연결 -> 단백질 3차원 접힘 예측 분석
  8. 8. Graph Information 8 emotional recognition
  9. 9. Convolutional Neural Networks 9
  10. 10. Convolutional AutoEncoder Deep Learning
  11. 11. Convolution Layer 11
  12. 12. Convolution Operation 12
  13. 13. Euler 13
  14. 14. Graph Theory History 14 - Euler - Seven Bridges of Königsberg
  15. 15. Abstraction using Graph 15
  16. 16. Vertex, Node, Edge 16
  17. 17. Knowlege Graph 17
  18. 18. Coal Power Plant Process Graph 18
  19. 19. subtree pattern of graph 19 height = 2
  20. 20. Graph Types 20
  21. 21. Graph Convolution Concept 21
  22. 22. Graph Convolutional Neural Networks (GCN) 22
  23. 23. Laplacian Operator 23
  24. 24. Laplacian 24
  25. 25. Image Laplacian 25
  26. 26. MRI Laplacian 26
  27. 27. 27
  28. 28. Adjacency Matrix (인접행렬) 28
  29. 29. Adjacency Matrix of Weighted Graph 29
  30. 30. Directed Graph Adjacency Matrix (out-direction) 30
  31. 31. 31 out-direction
  32. 32. 32 추천 시스템에서 나타나는 graph 입니다. 침대구매 --(0.6)-> 이불구매 --(0.8)-> 베개구매 자연현상이나 물리 화학적 공정을 표현할 때도 나타나는 graph 입니다. sun --(0.3)-> cloud --(0.1)-> rain
  33. 33. 33
  34. 34. 34 Gaussian distribution
  35. 35. Gradient of Scalar 35
  36. 36. Divergence of Vector 36
  37. 37. 37
  38. 38. Convolution Operation 38
  39. 39. Laplacian 39
  40. 40. Graph Laplacian ( L=D-W ) 40 (in-weight)
  41. 41. Graph Convolution Layer 41
  42. 42. Graph Convolution Propagation 42Cij : normalized constant
  43. 43. Graph Convolution Layer 43
  44. 44. 44
  45. 45. Convolution Kernel Size 45
  46. 46. Graph Convolution Kernel 46
  47. 47. Graphlet (index 0~72) 47 G pattern orbit index
  48. 48. Word Embedding 48
  49. 49. 49
  50. 50. Graphlet Degree Vector (GDV) 50
  51. 51. 51
  52. 52. Graph Downsampling & Graph Pooling 52
  53. 53. Heavy-edge Matching for Graph Coarsening 53 HEM
  54. 54. Sensor Noise Filtering with Graph 54
  55. 55. WL subtree kernel computing (1/5) 55 Weisfeiler-Lehman subtree method (와이스페일러-리만)
  56. 56. WL Multiset-labeling (2/5) 56
  57. 57. WL Label compression (3/5) 57
  58. 58. WL Relabeling (4/5) 58
  59. 59. WL Feature Vector (5/5) 59
  60. 60. Deep Graph Convolution Networks 60 WL method SortPooling Link WL convolution and Neural Networks for backpropagation
  61. 61. 1D Convolution after SortPooling layer 61
  62. 62. Graph Convolutional Neural Networks (GCN) 62
  63. 63. 63 Graph with Attention
  64. 64. New Protein Medicine 64
  65. 65. Molecular Graph 65
  66. 66. Molecular Fingerprint Representation 66
  67. 67. Protein Shape Element 67 alpha helix beta sheet
  68. 68. 68
  69. 69. Protein Folding 69
  70. 70. Protein Folding & Energy Level 70
  71. 71. Protein Binding Complex 71
  72. 72. Protein Folding Figurative 72
  73. 73. Graph Representation on Protein Structure 73
  74. 74. AlphaFold to predict protein foldings 74
  75. 75. Protein Medicine Search by GCN 75
  76. 76. DNA Sequence Convolutional NN 76
  77. 77. Gene Information of DNA 77
  78. 78. DNA Processing with Deep Learning 78
  79. 79. Predicting Protein-Protein interactions 79
  80. 80. 80
  81. 81. Multiple Sequence Alignment (MSA) 81
  82. 82. Sequence Conservation to Protein Fold Hot Spot 82
  83. 83. Drug Repurposing using Natural Language Text 83
  84. 84. Disease gene prioritization with GCN 84
  85. 85. Proteomic and cell biological dissection of mitochondrial networks 85
  86. 86. Contact 강신동 (주)지능도시 CEO ceo@idosi.com Deep Learning 관련 용역 (연구,개발) 86

×