Save 37% off PRO during our Black Friday Sale! »

Graphs, Edges & Nodes: Untangling the Social Web

Bd21ebabfbce06b235bc0516c1eb2912?s=47 Joël Perras
February 29, 2012

Graphs, Edges & Nodes: Untangling the Social Web

Facebook figures out people that you might already know, LinkedIn tells you how many degrees of separation there are between you and the CEO of Nokia, and LastFM suggests music based on your current listening habits. We’ll take a look at the basic theory behind how some of these features work, and some of the technology behind real-world implementations of these algorithms.

Bd21ebabfbce06b235bc0516c1eb2912?s=128

Joël Perras

February 29, 2012
Tweet

Transcript

  1. GRAPHS, EDGES & NODES: Untangling the SOCIAL WEB Wednesday, 29

    February, 12
  2. Wednesday, 29 February, 12

  3. KILLER ROBOTS Wednesday, 29 February, 12

  4. KILLER ROBOTS ... is not Wednesday, 29 February, 12

  5. MATH Wednesday, 29 February, 12

  6. MATH A LOT OF Wednesday, 29 February, 12

  7. MATH A SH*T TON OF Wednesday, 29 February, 12

  8. Broad Categories OF MACHINE LEARNING & GRAPH THEORY Wednesday, 29

    February, 12
  9. &Matrices Graphs Wednesday, 29 February, 12

  10. Graphs Wednesday, 29 February, 12

  11. Some Terminology Wednesday, 29 February, 12

  12. Some Terminology (SORRY) Wednesday, 29 February, 12

  13. Vertex NODE, POINT, JUNCTION, 0-SIMPLEX Wednesday, 29 February, 12

  14. Wednesday, 29 February, 12

  15. Edge ARC, BRANCH, LINE, LINK, 1-SIMPLEX Wednesday, 29 February, 12

  16. Wednesday, 29 February, 12

  17. Graph Wednesday, 29 February, 12

  18. Wednesday, 29 February, 12

  19. Wednesday, 29 February, 12

  20. Wednesday, 29 February, 12

  21. Wednesday, 29 February, 12

  22. 6 7 3 14 6 4 3 1 4 5

    7 13 4 19 9 12 15 7 2 10 9 6 1 3 7 Wednesday, 29 February, 12
  23. 6 7 3 14 6 4 3 1 4 5

    7 13 4 19 9 12 15 7 2 10 9 6 1 3 7 2 7 6 8 6 7 0 4 3 2 11 5 12 4 2 8 3 Wednesday, 29 February, 12
  24. Types of Graphs Wednesday, 29 February, 12

  25. Simple AT MOST ONE EDGE BETWEEN ANY PAIR OF NODES

    Wednesday, 29 February, 12
  26. Multigraph MULTIPLE EDGES BETWEEN SAME VERTICES ALLOWED Wednesday, 29 February,

    12
  27. Vectors & Points Wednesday, 29 February, 12

  28. Wednesday, 29 February, 12

  29. Wednesday, 29 February, 12

  30. Wednesday, 29 February, 12

  31. Wednesday, 29 February, 12

  32. Wednesday, 29 February, 12

  33. “Features” Wednesday, 29 February, 12

  34. Wednesday, 29 February, 12

  35. Wednesday, 29 February, 12

  36. Fat Protein Wednesday, 29 February, 12

  37. Fat Protein (39, 27) Wednesday, 29 February, 12

  38. Fat Protein (39, 27) 47.43 Wednesday, 29 February, 12

  39. Matrices Wednesday, 29 February, 12

  40. Item 1 Item 2 Item 3 Item 4 John Jane

    Cliff Cindy 2.5 4.5 1.0 4.0 1.0 3.5 2.0 2.5 4.5 5.0 4.0 3.5 2.0 2.5 3.5 4.0 Wednesday, 29 February, 12
  41. Item 1 Item 2 Item 3 Item 4 Item 5

    ... Item N John Jane Cindy André Chris Joan Alex ... Zack 2.5 4.5 1.0 4.0 4.5 ... 4.5 1.0 3.5 2.0 2.5 3.5 ... 5.0 4.5 5.0 4.0 3.5 5.0 ... 5.0 2.0 2.5 3.5 4.0 2.5 ... 1.0 2.5 4.5 1.0 4.0 4.5 ... 2.0 4.5 5.0 4.0 3.5 5.0 ... 4.5 2.0 4.0 3.5 3.5 4.5 ... 4.0 ... ... ... ... ... ... 5.0 2.5 4.5 1.0 4.0 1.0 ... 2.5 Wednesday, 29 February, 12
  42. Item 1 Item 2 Item 3 Item 4 Item 5

    ... Item N John Jane Cindy André Chris Joan Alex ... Zack 2.5 ? 1.0 ? ? ... ? ? ? ? 2.5 ? ... 5.0 ? 5.0 ? ? 5.0 ... ? 2.0 2.5 3.5 ? ? ... 1.0 ? ? ? ? ? ... ? ? ? ? 3.5 ? ... ? ? ? ? ? 4.5 ... 4.0 ... ... ... ... ... ... 5.0 ? ? 1.0 ? ? ... 2.5 Wednesday, 29 February, 12
  43. Classification Wednesday, 29 February, 12

  44. Classification BINARY Wednesday, 29 February, 12

  45. GOOD BAD vs Wednesday, 29 February, 12

  46. TRUE FALSE vs Wednesday, 29 February, 12

  47. RED BLUEvs Wednesday, 29 February, 12

  48. Wednesday, 29 February, 12

  49. Wednesday, 29 February, 12

  50. Wednesday, 29 February, 12

  51. Wednesday, 29 February, 12

  52. ? Wednesday, 29 February, 12

  53. Bayesian Networks PROBABILITY OF X, GIVEN Y. Wednesday, 29 February,

    12
  54. Decision Trees TREES OF OUTCOMES, COSTS & EXPECTED VALUES. Wednesday,

    29 February, 12
  55. Support Vector Machines MAXIMUM MARGIN HYPERPLANES Wednesday, 29 February, 12

  56. Artificial Neural Networks ... MAGIC! Wednesday, 29 February, 12

  57. Regression Wednesday, 29 February, 12

  58. Wednesday, 29 February, 12

  59. 0 10 Wednesday, 29 February, 12

  60. 0 10 8.2 Wednesday, 29 February, 12

  61. 0 10 8.2 Wednesday, 29 February, 12

  62. Linear Regression YOU’VE DONE THIS BEFORE. Wednesday, 29 February, 12

  63. Logistic Regression SOUNDS FANCIER THAN IT IS. Wednesday, 29 February,

    12
  64. Clustering Wednesday, 29 February, 12

  65. Wednesday, 29 February, 12

  66. Wednesday, 29 February, 12

  67. Wednesday, 29 February, 12

  68. Wednesday, 29 February, 12

  69. Wednesday, 29 February, 12

  70. Wednesday, 29 February, 12

  71. ? Wednesday, 29 February, 12

  72. ? Wednesday, 29 February, 12

  73. Wednesday, 29 February, 12

  74. & Network Flows Matchings Wednesday, 29 February, 12

  75. BJCP (Beer) Wednesday, 29 February, 12

  76. 70 Judges, 28 Categories BJCP (Beer) Wednesday, 29 February, 12

  77. BJCP (Beer) Judges have preferences Wednesday, 29 February, 12

  78. BJCP (Beer) At least 2 judges per category Wednesday, 29

    February, 12
  79. BJCP (Beer) Wednesday, 29 February, 12

  80. Wednesday, 29 February, 12

  81. Judges Wednesday, 29 February, 12

  82. Judges Categories Wednesday, 29 February, 12

  83. Judges Categories Wednesday, 29 February, 12

  84. Judges Categories S Wednesday, 29 February, 12

  85. Judges Categories S T Wednesday, 29 February, 12

  86. Judges Categories S T Wednesday, 29 February, 12

  87. Judges Categories S T Wednesday, 29 February, 12

  88. Judges Categories S T Wednesday, 29 February, 12

  89. Recommenders Wednesday, 29 February, 12

  90. Wednesday, 29 February, 12

  91. AMAZON NETFLIX PANDORA YELPHUNCH ... LINKEDIN FACEBOOK LAST.FM Wednesday, 29

    February, 12
  92. Content-Based Collaborative& Wednesday, 29 February, 12

  93. Items Users& Wednesday, 29 February, 12

  94. Item 1 Item 2 Item 3 Item 4 Item 5

    ... Item N John Jane Cindy André Chris Joan Alex ... Zack 2.5 ? 1.0 ? ? ... ? ? ? ? 2.5 ? ... 5.0 ? 5.0 ? ? 5.0 ... ? 2.0 2.5 3.5 ? ? ... 1.0 ? ? ? ? ? ... ? ? ? ? 3.5 ? ... ? ? ? ? ? 4.5 ... 4.0 ... ... ... ... ... ... 5.0 ? ? 1.0 ? ? ... 2.5 Wednesday, 29 February, 12
  95. Storage &Querying Wednesday, 29 February, 12

  96. Graph Databases NEO4J, ORIENTDB, INFINITEGRAPH Wednesday, 29 February, 12

  97. Column-Oriented Databases HBASE, CASSANDRA Wednesday, 29 February, 12

  98. Essential Python Libraries NUMPY, SCIPY, SCIKITS, NLTK, NETWORKX Wednesday, 29

    February, 12
  99. References The Algorithm Design Manual, Steve S. Skiena Introduction to

    Algorithms, Cormen, Leiserson, Rivest Flows in Networks, Ford, Fulkerson ... and a lot more. Wednesday, 29 February, 12
  100. QUESTIONS? Wednesday, 29 February, 12

  101. Fictive Kin Wednesday, 29 February, 12

  102. @jperras Joël Perras http://nerderati.com Wednesday, 29 February, 12