96 Matching Annotations
  1. Apr 2019
    1. ped an a
    2. me year, DeepM
    3. ort helpdesk, but also discuss morality, express opinions, and answer ge
    4. mans as a t
    5. ncingly int
    6. at could n
    7. l agent (A
    8. trained a conve
    9. omputer pr
    10. wer have dr
    11. r the past four
    12. ate of acceleration
    13. ike magic.
    14. more and
    15. a world fu
    16. es feeling left behi
    17. o does not un
    18. vation this century. A
    19. powerfully than
    20. ape our future
    21. tificial intelligence
    22. ning matters
    23. Why machine

      fgbgfb

    24. he Appendix
    25. ommendations i
    26. look at
    27. tc., take a
    28. rojects to atte
    29. extbooks to
    30. which course
    31. sted in figurin
    32. ou're more in
    33. hours.
    34. concept
    35. igh-level ma
    36. g up-to-sp
    37. s is a guide

      gfbgfbfgbgfb

    38. ledge of th
    39. iscussed,
    40. ut it isn’t nec
    41. sary to h
    42. bra, and c
    43. ramming, linea
    44. bility, statisti
    45. epts in
    46. e. Basic con
    47. ccessible to
    48. is intended to b
    49. who is curi
    50. bout ho
    51. h techni

      trgtrgtrgtrg

    52. rimer on m
    53. echnic
    54. ople who
    55. to speed o
    56. ho want to

      rtgtrgtrgtrg

    57. echnical

      rtgtrgtrg

    58. curriculum.

      trgtrgtrgtr

    59. ing your machine

      rtgtrgrtgtrg

    60. curated

      rgrtgtrgtrg

    61. deep reinfor

      rgrtgtrgtr

    62. ue learning p

      rgrtgrtgtrg

    63. esses. Q-lear

      rtgtrrtgtrg

    64. ing, policy lear

      rtgtrgrtgtrg

    65. olution

      rgrfgrrtgtrg

    66. m the brain. Co

      fevfvfvgv

    67. ploration and e

      dfvfdvdfv

    68. ning works. D

      dfvdfvdfvdfv

    69. Why, where, and

      dfvfdvdfvdfv

    70. omposition (S

      fdvdfvfdvdfv

    71. nalysis (PCA

      fdvdfvfvdfvfdv

    72. rincipal compone

      dfvdfvdfvdfv

    73. sionality re

      dfvdfvfdvfd

    74. ng: k-mean

      fdvdfvfdvfdv

    75. nce and machine

      dfvdfvfdvdfvdfv

    76. earning — past,

      dfvdfvdfvfd

    77. tions, overfitt

      dfvfdvfdvdfv

    78. earners:

      dfvdfvdfvdfvfd

    79. on-paramet

      dfvdfvfdvdfv

    80. SVMs.

      dvfvdfvdfv

    81. ession an

      fdvdfvfdvfdvdfv

    82. f classifica

      fdvdfvfdvfdv

    83. wo metho

      fvcfevfvfdv

    84. ient des

      erferferfref

    85. erfitting, and gr

      erfreferferf

    86. loss functions,

      erfrefref

    87. near regr

      referfref

    88. wer key. I

      erferfref

    89. arning with an

      erfref

    90. he big pict

      erferfref

    91. Roadmap

      rferfer

    92. nations

      frfrfref

    93. Simple, plain-English

      test

    94. Humans
    95. Learning for
    96. Machine