ML Session n°4

2696500a913e29a26f38115f8ea56f71?s=47 Adrien Couque
April 05, 2017
Technology
0
12

ML Session n°4

2696500a913e29a26f38115f8ea56f71?s=128

Adrien Couque

April 05, 2017
Tweet

More Decks by Adrien Couque

See All by Adrien Couque
2696500a913e29a26f38115f8ea56f71?s=48 acq
0
8
2696500a913e29a26f38115f8ea56f71?s=48 acq
0
32
2696500a913e29a26f38115f8ea56f71?s=48 acq
0
9
2696500a913e29a26f38115f8ea56f71?s=48 acq
0
10
2696500a913e29a26f38115f8ea56f71?s=48 acq
0
7
2696500a913e29a26f38115f8ea56f71?s=48 acq
0
11
2696500a913e29a26f38115f8ea56f71?s=48 acq
1
9
2696500a913e29a26f38115f8ea56f71?s=48 acq
0
5
2696500a913e29a26f38115f8ea56f71?s=48 acq
0
130

Other Decks in Technology

See All in Technology
A73e465566ed41cd2b66b7d889b31666?s=48 maiamea
1
550
1e8c5eaf563f965d3ba48b0054b1d955?s=48 shoichiron
8
2.7k
23190387d424e33d6a1a807cea1e0469?s=48 osamtimizer
1
330
405fe9ab689473f267e2cfbd95f78c75?s=48 kyonmm
0
1.5k
45550674a29d1684dea142290be996a4?s=48 gdm
1
100
457ada693e168bd1102fec3914040b5d?s=48 uipath_friends
0
120
966e29b84ae7dbde170f66b0bc75b7a6?s=48 ishiayaya
1
200
1b177b37d966f573b1df5d7218a5f560?s=48 k2wanko
1
200
8a84268593355816432ceaf78777d585?s=48 dena_tech
0
910
Cc8a208e174943d1da814783841abd50?s=48 shinodogg
2
170
21a4b941766d805333e11c5766be43b4?s=48 takahashim
10
850
B2fefbb30aba7c25bbe0c8819791631a?s=48 gunnargrosch
1
340

Featured

See All Featured
91cefdf141106fa10674aae74ce05890?s=48 yeseniaperezcruz
297
31k
7fa6101cd43067653cf4ac6c7ca54305?s=48 akmur
252
19k
0bce06bd06ee7a2c4f5500f25dcf7f18?s=48 paulrobertlloyd
69
1.3k
C7393b7ba7ec9c8890dd77d209fbb3c9?s=48 maltzj
499
36k
F716e5f737fcfb03f2cf8d1a184f1dbe?s=48 nonsquared
79
3.2k
6bb82b13cda86d3b821fa44100335ddf?s=48 thoeni
3
360
96270e4c3e5e9806cf7245475c00b275?s=48 addyosmani
492
110k
95d9f37115fbb0d13135d0f77132f856?s=48 morganepeng
11
690
Ecdea9b9714877b86cee08458f085481?s=48 trallard
10
440
Af6a12710770ad9a7cfd08c97efd40d3?s=48 pedronauck
649
110k
E4f5d494ebdc9e7cce1aecf3ce3e8bc1?s=48 shpigford
366
42k
06f8b41980eb4c577fa40c41d5030c19?s=48 keathley
15
520

Transcript

  1. ML: regularization and neural networks March 2017

  2. Recap

  3. Recap: linear regression

  4. Recap: polynomial regression

  5. Recap: gradient descent

  6. Regularization

  7. Normalization Goal : have all features be equivalent (in size)

    Rescaling : Standardization :

  8. Regularization : goal

  9. Regularization Before : Now : Forces values to stay low

  10. Neural networks

  11. Demo: Tensorflow Playground

  12. Biological neuron

  13. Artificial neuron: Perceptron

  14. Teaching a neuron

  15. Artifical neuron : activation function

  16. Most common activation functions Identity Sigmoid Tanh ReLU

  17. Teaching a neuron

  18. Demo: simple network, but the hard way (92%)

  19. Demo: simple network, but the hard way (92%)

  20. Artificial neuron -> Artificial neural network

  21. Artificial neuron -> Artificial neural network

  22. Teaching a neural net

  23. Demo: Tensorflow Playground

  24. Demo: layered network, still the hard way (97%)

  25. Questions? March 2017