Slide 1

Slide 1 text

Fantastic Models and Where to Find Them Rishit Dagli High School TEDx, TED-Ed Speaker rishit_dagli Rishit-dagli

Slide 2

Slide 2 text

Fantastic Models and Where to Find Them Rishit Dagli

Slide 3

Slide 3 text

TensorFlow Hub rishit_dagli A repository of trained machine learning models ready for fine-tuning and deployable anywhere

Slide 4

Slide 4 text

TensorFlow Hub rishit_dagli

Slide 5

Slide 5 text

● High School Student ● TEDx and 2xTed-Ed Speaker ● I contribute to TF Hub ● I ❤ ML Research ● My coordinates - www.rishit.tech $whoami rishit_dagli Rishit-dagli

Slide 6

Slide 6 text

● Devs who have worked on Deep Learning Models (Keras) Ideal Audience rishit_dagli

Slide 7

Slide 7 text

rishit_dagli ● Off the shelf inference with SoTA machine learning models Could be super helpful rishit_dagli

Slide 8

Slide 8 text

rishit_dagli ● ● You do need to ask yourself: ○ Is there enough information in P to represent Q? ○ how much new data? ○ can unlabelled data do it? ○ what’s the right mix of P and Q data? ○ How far is from P from Q? Transfer Learning rishit_dagli

Slide 9

Slide 9 text

rishit_dagli ● ● You do need to ask yourself: ○ Is there enough information in P to represent Q? ○ how much new data? ○ can unlabelled data do it? ○ what’s the right mix of P and Q data? ○ How far is from P from Q? ● Samory Kpotufe: Some Recent Insights on Transfer-Learning Transfer Learning rishit_dagli

Slide 10

Slide 10 text

rishit_dagli ● ● You do need to ask yourself: ○ Is there enough information in P to represent Q? ○ how much new data? ○ can unlabelled data do it? ○ what’s the right mix of P and Q data? ○ How far is from P from Q? ● You can do this easily with TF Hub too! Transfer Learning rishit_dagli

Slide 11

Slide 11 text

rishit_dagli ● Less data Could be super helpful rishit_dagli

Slide 12

Slide 12 text

rishit_dagli ● Less data ● Less domain expertise Could be super helpful rishit_dagli

Slide 13

Slide 13 text

rishit_dagli ● Less data ● Less domain expertise ● for different domains including image, video, audio etc. Could be super helpful rishit_dagli

Slide 14

Slide 14 text

rishit_dagli ● Less data ● Less domain expertise ● for different domains including image, video, audio etc. ● Take advantage of SoTA machine learning models Could be super helpful rishit_dagli

Slide 15

Slide 15 text

rishit_dagli Ready to Use rishit_dagli Credits: @TheSandeepGupta

Slide 16

Slide 16 text

No content

Slide 17

Slide 17 text

Style Transfer

Slide 18

Slide 18 text

Style Transfer rishit_dagli

Slide 19

Slide 19 text

Style Transfer rishit_dagli

Slide 20

Slide 20 text

Style Transfer rishit_dagli

Slide 21

Slide 21 text

Classification Prediction: Goldfish, Carassius_auratus

Slide 22

Slide 22 text

Image Classification rishit_dagli

Slide 23

Slide 23 text

rishit_dagli bit.ly/hub-classification

Slide 24

Slide 24 text

Fine tune BERT

Slide 25

Slide 25 text

Fine tune BERT rishit_dagli Classify Text with BERT

Slide 26

Slide 26 text

Fine tune BERT rishit_dagli Classify Text with BERT

Slide 27

Slide 27 text

Fine tune BERT rishit_dagli Classify Text with BERT

Slide 28

Slide 28 text

Fine tune BERT rishit_dagli Classify Text with BERT

Slide 29

Slide 29 text

Fine tune BERT rishit_dagli Classify Text with BERT

Slide 30

Slide 30 text

Fine tune BERT rishit_dagli Classify Text with BERT

Slide 31

Slide 31 text

Fine tune BERT rishit_dagli Classify Text with BERT

Slide 32

Slide 32 text

rishit_dagli And more... TF Hub for other tasks rishit_dagli

Slide 33

Slide 33 text

rishit_dagli tensorflow.org/hub/publish Publish your own models

Slide 34

Slide 34 text

rishit_dagli bit.ly/tfhub-deck Slides here

Slide 35

Slide 35 text

Thank You rishit_dagli Rishit-dagli