Tweet
Tweet

Slide 1

Slide 1 text

Decentralized and Personalized AI, with Privacy by Design Charmi Chokshi, Machine Learning Engineer @CharmiChokshi

Slide 2

Slide 2 text

It’s Diwali in India, let’s have some noise in the house!!!

Slide 3

Slide 3 text

Let’s get to know each other?

Slide 4

Slide 4 text

Find out five similarities with person sitting next to you.*

Slide 5

Slide 5 text

What is the most craziest thing you want to do in the next one year?

Slide 6

Slide 6 text

What is the most coolest project (an AI-based) you have ever worked on?

Slide 7

Slide 7 text

What do you wish to get out of this session?

Slide 8

Slide 8 text

Session plan: ● Decentralized Data ● Federated Computation ○ Privacy principles ● Federated Learning ○ Privacy technologies ● Ideathon…!!!

Slide 9

Slide 9 text

No content

Slide 10

Slide 10 text

No content

Slide 11

Slide 11 text

No content

Slide 12

Slide 12 text

No content

Slide 13

Slide 13 text

No content

Slide 14

Slide 14 text

No content

Slide 15

Slide 15 text

No content

Slide 16

Slide 16 text

No content

Slide 17

Slide 17 text

No content

Slide 18

Slide 18 text

No content

Slide 19

Slide 19 text

No content

Slide 20

Slide 20 text

No content

Slide 21

Slide 21 text

No content

Slide 22

Slide 22 text

No content

Slide 23

Slide 23 text

No content

Slide 24

Slide 24 text

No content

Slide 25

Slide 25 text

No content

Slide 26

Slide 26 text

No content

Slide 27

Slide 27 text

No content

Slide 28

Slide 28 text

No content

Slide 29

Slide 29 text

No content

Slide 30

Slide 30 text

No content

Slide 31

Slide 31 text

No content

Slide 32

Slide 32 text

No content

Slide 33

Slide 33 text

No content

Slide 34

Slide 34 text

No content

Slide 35

Slide 35 text

No content

Slide 36

Slide 36 text

No content

Slide 37

Slide 37 text

No content

Slide 38

Slide 38 text

No content

Slide 39

Slide 39 text

No content

Slide 40

Slide 40 text

No content

Slide 41

Slide 41 text

No content

Slide 42

Slide 42 text

No content

Slide 43

Slide 43 text

No content

Slide 44

Slide 44 text

No content

Slide 45

Slide 45 text

No content

Slide 46

Slide 46 text

No content

Slide 47

Slide 47 text

No content

Slide 48

Slide 48 text

No content

Slide 49

Slide 49 text

No content

Slide 50

Slide 50 text

No content

Slide 51

Slide 51 text

No content

Slide 52

Slide 52 text

No content

Slide 53

Slide 53 text

No content

Slide 54

Slide 54 text

No content

Slide 55

Slide 55 text

No content

Slide 56

Slide 56 text

No content

Slide 57

Slide 57 text

No content

Slide 58

Slide 58 text

No content

Slide 59

Slide 59 text

No content

Slide 60

Slide 60 text

It’s time for the Ideathon!!!

Slide 61

Slide 61 text

Let’s have a look at our smartphones* *or at our lives

Slide 62

Slide 62 text

Can you spot any app to embed Federated Learning into it?

Slide 63

Slide 63 text

Let’s figure out the Model Learning pipeline

Slide 64

Slide 64 text

64 Data acquisition Model Deployment Data Cleaning Feature Engineering Model Validation Model Monitoring Model Selection Model Testing Model Training Hyper parameter tuning

Slide 65

Slide 65 text

65 Data acquisition Model Deployment Data Cleaning Feature Engineering Model Validation Model Monitoring Model Selection Model Testing Model Training Hyper parameter tuning

Slide 66

Slide 66 text

66 Data acquisition Model Deployment Data Cleaning Feature Engineering Model Validation Model Monitoring Model Selection Model Testing Model Training Hyper parameter tuning

Slide 67

Slide 67 text

67 Data acquisition Model Deployment Data Cleaning Feature Engineering Model Validation Model Monitoring Model Selection Model Testing Model Training Hyper parameter tuning

Slide 68

Slide 68 text

68 Data acquisition Model Deployment Data Cleaning Feature Engineering Model Validation Model Monitoring Model Selection Model Testing Model Training Hyper parameter tuning

Slide 69

Slide 69 text

69 Data acquisition Model Deployment Data Cleaning Feature Engineering Model Validation Model Monitoring Model Selection Model Testing Model Training Hyper parameter tuning

Slide 70

Slide 70 text

70 Data acquisition Model Deployment Data Cleaning Feature Engineering Model Validation Model Monitoring Model Selection Model Testing Model Training Hyper parameter tuning

Slide 71

Slide 71 text

71 Data acquisition Model Deployment Data Cleaning Feature Engineering Model Validation Model Monitoring Model Selection Model Testing Model Training Hyper parameter tuning

Slide 72

Slide 72 text

72 Data acquisition Model Deployment Data Cleaning Feature Engineering Model Validation Model Monitoring Model Selection Model Testing Model Training Hyper parameter tuning

Slide 73

Slide 73 text

73 Data acquisition Model Deployment Data Cleaning Feature Engineering Model Validation Model Monitoring Model Selection Model Testing Model Training Hyper parameter tuning

Slide 74

Slide 74 text

74 Data acquisition Model Deployment Data Cleaning Feature Engineering Model Validation Model Monitoring Model Selection Model Testing Model Training Hyper parameter tuning

Slide 75

Slide 75 text

Brainstorm How could federated learning be applied to the ways you use a computer* each day? * Laptop, phone, tablet, etc.

Slide 76

Slide 76 text

Finalize Your Idea Spend 5 minutes agreeing as a group what your final idea will be.

Slide 77

Slide 77 text

Finalize Your Idea Design - Develop - Deploy

Slide 78

Slide 78 text

Keep building your Ideas!

Slide 79

Slide 79 text

https://federated.withgoogle.com/

Slide 80

Slide 80 text

Sharing Your Ideas What would you say at the Product Launch Party?

Slide 81

Slide 81 text

Sharing Your Ideas Do not forget to invite us!! @mozillafestival @CharmiChokshi

Slide 82

Slide 82 text

References ● Federated Optimization: Distributed Optimization Beyond the Datacenter, Jakub Konecny, H. Brendan McMahan, Daniel Ramage, 2015 ● Decentralized Collaborative Learning of Personalized Models over Networks Paul Vanhaesebrouck, Aurélien Bellet, Marc Tommasi, 2017 ● Towards federated learning at scale: system design, Keith Bonawitz Hubert Eichner and al., 2019 ● https://federated.withgoogle.com/ ● https://www.youtube.com/watch?v=89BGjQYA0uE

Slide 83

Slide 83 text

Questions? Suggestions? Comments? Charmi Chokshi, Machine Learning Engineer @CharmiChokshi

Slide 84

Slide 84 text

Thank you! Happy Learning :) Charmi Chokshi, ML Engineer, Shipmnts.com LinkedIn, Twitter: @CharmiChokshi Email: charmichokshi@gmail.com