input(ML_Enthusiast) : output(ML_Engineer)

Slide 1

Slide 1 text

Charmi Chokshi, Shipmnts.com @CharmiChokshi input(ML_Enthusiast) : output(ML_Engineer)

Slide 2

Slide 2 text

Last Session...

Slide 3

Slide 3 text

Last Session...

Slide 4

Slide 4 text

પણ સનેડો હજી બાકી છે!!!

Slide 5

Slide 5 text

Let’s have a look at our smartphones

Slide 6

Slide 6 text

Can you spot any app which uses Machine Learning?

Slide 7

Slide 7 text

Answer the following: - What is the primary functionality / feature of the app? - How it has embedded ML to fulfil it?

Slide 8

Slide 8 text

Let’s figure out ML Pipeline

Slide 9

Slide 9 text

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

Slide 10

Slide 10 text

Let’s figure out the correct order

Slide 11

Slide 11 text

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

Slide 12

Slide 12 text

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

Slide 13

Slide 13 text

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

Slide 14

Slide 14 text

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

Slide 15

Slide 15 text

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

Slide 16

Slide 16 text

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

Slide 17

Slide 17 text

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

Slide 18

Slide 18 text

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

Slide 19

Slide 19 text

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

Slide 20

Slide 20 text

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

Slide 21

Slide 21 text

Design - Develop - Deploy

Slide 22

Slide 22 text

Let’s form groups 2 mins

Slide 23

Slide 23 text

What is we are gonna do? ● 3 different Problems ● 3 different Deployment Pipelines ● 3 different Solutions

Slide 24

Slide 24 text

What is we are gonna do? 1. Smile and Pay we know... ○ How about building a Smile and Enter system for the next #DevFestAhm

Slide 25

Slide 25 text

What is we are gonna do? 2. Prediction of the next word on your phones such as GBoard, a keyboard by

Slide 26

Slide 26 text

What is we are gonna do? 3. Integration of the Object Detection System on Maps

Slide 27

Slide 27 text

Design 5 mins

Slide 28

Slide 28 text

Don’t forget to tweet your design! @GDGAhmedabad @WTMAhmedabad @GDGCloudAhm @CharmiChokshi #DevFest #DevFestAhm

Slide 29

Slide 29 text

Develop 5 mins

Slide 30

Slide 30 text

Deploy 5 mins

Slide 31

Slide 31 text

What would you say at your product launch party? 5 mins

Slide 32

Slide 32 text

Don’t forget to invite us at the party…!! @GDGAhmedabad @WTMAhmedabad @GDGCloudAhm @CharmiChokshi #DevFest #DevFestAhm