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
29
2696500a913e29a26f38115f8ea56f71?s=48 acq
0
9
2696500a913e29a26f38115f8ea56f71?s=48 acq
0
10
2696500a913e29a26f38115f8ea56f71?s=48 acq
0
7
2696500a913e29a26f38115f8ea56f71?s=48 acq
0
8
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
229b1596ce57cd0935a2bacd410d87a0?s=48 aaaddress1
1
1.5k
5b392dc79d5b6d1dab580bf60e26fb7c?s=48 nitya
0
210
706ff501573a736401aa4de5adc88e05?s=48 nihonbuson
3
1k
783718ebd2faaa896d4cb347835c07fb?s=48 tarotaro0
0
320
9c42c4bc1d91c409d754da88c91cb2ef?s=48 kur0cky
1
230
9e7a653ed313b3da4b263a772bfc5026?s=48 clustervr
0
280
66fabad28b40a99387ab582cd0e94a2d?s=48 hiromaaa03
1
110
893dd6e1aa73c35621327c385cb27207?s=48 konnnnnok
0
130
877f92a3597118cda2715790fa170ad4?s=48 benzookapi
0
110
Ad22fcf5773b906c08330f4d57242212?s=48 inductor
3
790
5d715b858124e0dd59af1a92e4397acd?s=48 y_temp4
0
110
7843111608e155f89877c4faca12697e?s=48 shuntafurukawa
0
240

Featured

See All Featured
95d9f37115fbb0d13135d0f77132f856?s=48 morganepeng
4
430
91cefdf141106fa10674aae74ce05890?s=48 yeseniaperezcruz
296
30k
79acae287842acf29084005533a7fb3b?s=48 hursman
103
9k
3ab1249be442027903e1180025340b3f?s=48 reverentgeek
17
1.2k
F29327647a9cff5c69618bae420792ea?s=48 tenderlove
49
3.2k
Fe6b81005d1553accd6b2a28f6a2bef1?s=48 phodgson
83
3.8k
7edec06b5435e0dac07a353b2cc26253?s=48 geeforr
330
29k
027d1ebf66cc039a0bd3b55eeadbe75d?s=48 sachag
447
35k
5f2da528927a2ec9ba4fec2069cbc958?s=48 kneath
218
14k
A60068bce2e73de3a37ca9d2dbe36092?s=48 bryan
28
3.1k
282d599b414022eba5096510f675b6e2?s=48 chrislema
169
14k
1b8ad785acdd1ce1c99914b1c2a4e10e?s=48 sugarenia
230
750k

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