SlideShare a Scribd company logo
1 of 74
Design
How to solve a problem using
Deep Learning
AI for Good Workshop
July 2019
Session 3
https://sites.google.com/view/AIforEveryone
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Key Learning objective
for Day 1
How to solve a problem with Deep Learning ?
How to design an neural network architecture?
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Quiz #1
Is it possible to map hand signs for deaf  speech
 Hand signs   Speech
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
A B
•
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Quiz #2
Is it possible to “see the depth” for visual impaired
 Yes / no ?
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Quiz #2
Is it possible to feel the depth for visual impaired
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Topics in this presentation
•New way to think from today !
• How to use Deep Learning to solve any problem
• How to model & architect Neural Networks
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
New way to think from today !
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
New way to think from today !
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Deep Learning idea-a-thon:
How to solve a problem
by designing novel neural network architectures?
CNN
RNN
Fully
Connected
Merge
CNN is suitable architecture to extract
features out of any data that has
spatial relationships. For example, An
photo image spatial info..or info
spread across space
In general, a recurrent neural network could
be considered as the best neural network
model for extracting features out of
temporal data. A temporal data is basically
a data that varies over time such as ECG,
music, speech, sentences, words. LSTM is
a advanced RNN
To classify / predict
To combine the learnings of
two neural networks.
(to combine the power of 2
people’s brains)
Attention
To learn to focus on the
most important aspects to
achieve a particular task
Generative
Deep Learning
To model creative tasks as
to compose a music or
to come up a painting
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Our inspiration / acknowledgements
Friendly approaches :
1) KERAS.io
François Chollet’s
Book on “Deep Learning with Python”
2) Deeplearning.ai (Coursera.org)
Andrew Ng
3) Udacity Deep Learning Free course
4) Google Machine Learning Course
https://developers.google.com/machine-learning/crash-course/
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
More inspiration/ acknowledgements
Excellent Resources
• Stanford cs231 n
http://cs231n.stanford.edu
• MIT Deep Learning
http://introtodeeplearning.com/
https://deeplearning.mit.edu
• IIT Madras
my classes notes with Prof. Anurag (Deep Learning)
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Message: Using
Representation learning to
learn to represent A as B
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Learning objective:
How did the magic happen?
Deep
Learning
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Learning objective:
How did the magic happen?
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Learn to map Xy
• Examples of x, y
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
A  B
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Fun activity
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Learning objective:
How do solve a problem
using Deep Learning?
Case study: self driving car
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Camera view ? steering angle
•
Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car
Credits: Nvidia
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
•
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Learn to map x->y
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
What is the function to map x->y
•
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Key Learning objective
for Day 1
How to solve a problem with Deep Learning ?
How to design an neural network architecture?
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Architecture patterns
Neural Network Design Pattern #1
classification problems
CNN
Fully
Connected
Prediction of what
of objects is in this
photo
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #1
CNN
Fully
Connected
Turn car left
Turn car right
Don’t Turn the car
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #1
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #1
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Architecture patterns
Neural Network Design Pattern #2
Regression problems
CNN
Fully
Connected
Continuous number
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #2
Regression problems
CNN
Fully
Connected
Turn the car by 10 degrees
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #2
Regression problems
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #2
Regression problems
•
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Architecture patterns
Neural Network Design Pattern #3
multimodal classification
CNN
Fully
Connected
Predicted
class
RNN
Merge
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Architecture patterns
Neural Network Design Pattern #3
multimodal classification
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Architecture patterns
Neural Network Design Pattern #3
multimodal classification
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Quiz
Neural Network Design Pattern #3
multimodal classification
•
Quiz: What was x and y in the problem?
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Quiz
Neural Network Design Pattern #3
• Quiz: What was x and y in the problem?
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Quiz
multimodal classification
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Answering Visual Questions from Blind People
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #3
multimodal classification
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Architecture patterns
Neural Network Design Pattern #3
multimodal classification
•
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #3
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Architecture patterns
Neural Network Design Pattern #4
video question answering
CNN
Fully
Connected
Predicted
class
RNN
Merge
Video
Question
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Architecture patterns
Neural Network Design Pattern #4
video question answering
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #4
video question answering
•
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #4
video question answering
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #4
video question answering
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #4
video question answering
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #4
video question answering
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #4
video question answering
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Architecture patterns
Neural Network Design Pattern #5
image question answering
CNN
Answer
(text)
RNN
Merge
Image
(photo)
Question
(text)
RNN
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #5
image question answering
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Architecture patterns
Neural Network Design Pattern #6
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #6
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Architecture patterns
Neural Network Design Pattern #7
image to image translation
CNN
Image
(text)
Image
(photo)
CNN
Features of
the image
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #7
image to image translation
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #7
image to image translation
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #7
image to image translation
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Neural Network Design Pattern #7
image to image translation
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Quiz
Can a neural network output 2 types
of output?
• How to architect Multi output network?
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Quiz
Multi output network
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Quiz
how to extract features from multiple
sources ?
• I have a input of audio and video and text. How to combine the features
from all 3?
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Quiz
how to extract features from multiple sources ?
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
What did you learn?
(Day 1)
How to solve a problem with Deep Learning ?
How to design an neural network architecture?
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Key ideas to remember
You can map any thing to anything with Deep Learning AB
• Anything  Machine Learns to map  Anything
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Key ideas to remember
How to design a architectures to handle various types of A  B
How to design this architecture?
CNN / RNN ?
Fully Connected or RNN ?
Predicted
class
RNN /
Fully connected ?
Merge / Attention ?
Video
Question
A  --------------------------------------------------------------------------------------------------------------------------  B
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Key ideas to remember
From architecture to code ? (just learn early glimpse of how code looks like.)
Just 1 page of code is enough for a complex problems such as video question answering
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Key ideas to remember
If you didn’t understand the code*, just don’t worry.
• Why not to worry?
• Solving the video question answering problem was not possible until 2017.
• To solve this problem, it required dozens of experts in Google lab to dedicate 6 months of effort!
*code = code in the previous slide
Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
Team activity
idea-a-ton
Goal of this thinking activity
How to solve a problem with Deep Learning ?
How to design an neural network architecture?

More Related Content

What's hot

Google Changes for Bed & Breakfasts in 2013
Google Changes for Bed & Breakfasts in 2013Google Changes for Bed & Breakfasts in 2013
Google Changes for Bed & Breakfasts in 2013Brandon Dennis
 
GOOGLE ALGORITHM - 2014 A LOOK SEO
GOOGLE ALGORITHM - 2014 A LOOK SEOGOOGLE ALGORITHM - 2014 A LOOK SEO
GOOGLE ALGORITHM - 2014 A LOOK SEOVENKATESH S
 
eTail West 2017: SEO Audits
eTail West 2017: SEO AuditseTail West 2017: SEO Audits
eTail West 2017: SEO AuditsEric Wu
 
Google SEO 2013 - Hummingbird and Beyond
Google SEO 2013 - Hummingbird and BeyondGoogle SEO 2013 - Hummingbird and Beyond
Google SEO 2013 - Hummingbird and BeyondDorian Karthauser
 
YouTube Optimization Tips for SEOs #SMXAdvanced
YouTube Optimization Tips for SEOs #SMXAdvancedYouTube Optimization Tips for SEOs #SMXAdvanced
YouTube Optimization Tips for SEOs #SMXAdvancedAleyda Solís
 
Google Humming Bird Algorithm Update
Google Humming Bird Algorithm UpdateGoogle Humming Bird Algorithm Update
Google Humming Bird Algorithm UpdateMake It Rain
 
SEO In 2022: Google Discover and Microsite SERPs - (SEMrush Webinar)
SEO In 2022: Google Discover and Microsite SERPs - (SEMrush Webinar)SEO In 2022: Google Discover and Microsite SERPs - (SEMrush Webinar)
SEO In 2022: Google Discover and Microsite SERPs - (SEMrush Webinar)Evolving SEO
 
Semantic SEO in 2017 & Beyond: The Ultimate Guide
Semantic SEO in 2017 & Beyond: The Ultimate GuideSemantic SEO in 2017 & Beyond: The Ultimate Guide
Semantic SEO in 2017 & Beyond: The Ultimate GuideLissa Anderson
 
SearchLove London 2015 | Will Critchlow | Practical Tips for the Future of ...
SearchLove London 2015 |  Will Critchlow |  Practical Tips for the Future of ...SearchLove London 2015 |  Will Critchlow |  Practical Tips for the Future of ...
SearchLove London 2015 | Will Critchlow | Practical Tips for the Future of ...Distilled
 

What's hot (11)

Google Changes for Bed & Breakfasts in 2013
Google Changes for Bed & Breakfasts in 2013Google Changes for Bed & Breakfasts in 2013
Google Changes for Bed & Breakfasts in 2013
 
GOOGLE ALGORITHM - 2014 A LOOK SEO
GOOGLE ALGORITHM - 2014 A LOOK SEOGOOGLE ALGORITHM - 2014 A LOOK SEO
GOOGLE ALGORITHM - 2014 A LOOK SEO
 
Ahrefs Tutorial
Ahrefs TutorialAhrefs Tutorial
Ahrefs Tutorial
 
eTail West 2017: SEO Audits
eTail West 2017: SEO AuditseTail West 2017: SEO Audits
eTail West 2017: SEO Audits
 
Google SEO 2013 - Hummingbird and Beyond
Google SEO 2013 - Hummingbird and BeyondGoogle SEO 2013 - Hummingbird and Beyond
Google SEO 2013 - Hummingbird and Beyond
 
YouTube Optimization Tips for SEOs #SMXAdvanced
YouTube Optimization Tips for SEOs #SMXAdvancedYouTube Optimization Tips for SEOs #SMXAdvanced
YouTube Optimization Tips for SEOs #SMXAdvanced
 
Google Humming Bird Algorithm Update
Google Humming Bird Algorithm UpdateGoogle Humming Bird Algorithm Update
Google Humming Bird Algorithm Update
 
SEO In 2022: Google Discover and Microsite SERPs - (SEMrush Webinar)
SEO In 2022: Google Discover and Microsite SERPs - (SEMrush Webinar)SEO In 2022: Google Discover and Microsite SERPs - (SEMrush Webinar)
SEO In 2022: Google Discover and Microsite SERPs - (SEMrush Webinar)
 
Semantic SEO in 2017 & Beyond: The Ultimate Guide
Semantic SEO in 2017 & Beyond: The Ultimate GuideSemantic SEO in 2017 & Beyond: The Ultimate Guide
Semantic SEO in 2017 & Beyond: The Ultimate Guide
 
SearchLove London 2015 | Will Critchlow | Practical Tips for the Future of ...
SearchLove London 2015 |  Will Critchlow |  Practical Tips for the Future of ...SearchLove London 2015 |  Will Critchlow |  Practical Tips for the Future of ...
SearchLove London 2015 | Will Critchlow | Practical Tips for the Future of ...
 
Seo Part 1
Seo Part 1Seo Part 1
Seo Part 1
 

Similar to Deep Learning: Session 2 how to architect

2 day Deep Learning Workshop - Session 3
2 day Deep Learning Workshop - Session 3 2 day Deep Learning Workshop - Session 3
2 day Deep Learning Workshop - Session 3 Rajagopal A
 
Session 5 coding handson Tensorflow
Session 5 coding handson Tensorflow Session 5 coding handson Tensorflow
Session 5 coding handson Tensorflow Rajagopal A
 
Deep Learning: Session 3 : How to succeed
Deep Learning: Session 3 : How to succeedDeep Learning: Session 3 : How to succeed
Deep Learning: Session 3 : How to succeedRajagopal A
 
Deep Learning Session 1 : bright future for you summary
Deep Learning Session 1 : bright future for you summaryDeep Learning Session 1 : bright future for you summary
Deep Learning Session 1 : bright future for you summaryRajagopal A
 
2 day Deep Learning Workshop at Karunya - Session 2
2 day Deep Learning Workshop at Karunya - Session 22 day Deep Learning Workshop at Karunya - Session 2
2 day Deep Learning Workshop at Karunya - Session 2Rajagopal A
 
Digital technology to generate save money gem conf cambridge 2014 reduced for...
Digital technology to generate save money gem conf cambridge 2014 reduced for...Digital technology to generate save money gem conf cambridge 2014 reduced for...
Digital technology to generate save money gem conf cambridge 2014 reduced for...Martin Bazley
 
RSC SE Teaching toolkit no 8 Todaysmeet, QR codes and Slideshare - Jane Macke...
RSC SE Teaching toolkit no 8 Todaysmeet, QR codes and Slideshare - Jane Macke...RSC SE Teaching toolkit no 8 Todaysmeet, QR codes and Slideshare - Jane Macke...
RSC SE Teaching toolkit no 8 Todaysmeet, QR codes and Slideshare - Jane Macke...Jane Mackenzie
 
DevLearn 2018 - Designing AR Experiences for Performance Support
DevLearn 2018 -  Designing AR Experiences for Performance SupportDevLearn 2018 -  Designing AR Experiences for Performance Support
DevLearn 2018 - Designing AR Experiences for Performance SupportChad Udell
 
MIT Deep Learning Basics: Introduction and Overview by Lex Fridman
MIT Deep Learning Basics: Introduction and Overview by Lex FridmanMIT Deep Learning Basics: Introduction and Overview by Lex Fridman
MIT Deep Learning Basics: Introduction and Overview by Lex FridmanPeerasak C.
 
Sp12_Week3 complete
Sp12_Week3 completeSp12_Week3 complete
Sp12_Week3 completeeducw200
 
Building Innovative Products with Agile
Building Innovative Products with AgileBuilding Innovative Products with Agile
Building Innovative Products with AgileSean Ammirati
 
Producing Online Educational Videos
Producing Online Educational VideosProducing Online Educational Videos
Producing Online Educational VideosRichard Harrington
 
Improving WordPress Themes & Plugins Support Documentation
Improving WordPress Themes & Plugins Support DocumentationImproving WordPress Themes & Plugins Support Documentation
Improving WordPress Themes & Plugins Support DocumentationGloria Antonelli
 
What is good design, from One Big Field
What is good design, from One Big FieldWhat is good design, from One Big Field
What is good design, from One Big FieldFergus Roche
 
Analytics For SEOs - Mozcation Portsmouth 11/7/12
Analytics For SEOs - Mozcation Portsmouth 11/7/12Analytics For SEOs - Mozcation Portsmouth 11/7/12
Analytics For SEOs - Mozcation Portsmouth 11/7/12Evolving SEO
 
Lisa14 - Transforming to a Culture of Continuous Improvement
Lisa14 - Transforming to a Culture of Continuous ImprovementLisa14 - Transforming to a Culture of Continuous Improvement
Lisa14 - Transforming to a Culture of Continuous ImprovementCourtney Kissler
 
CLSA Technology in Education and Leadership Activities Workshop
CLSA Technology in Education and Leadership Activities WorkshopCLSA Technology in Education and Leadership Activities Workshop
CLSA Technology in Education and Leadership Activities WorkshopChristian Choquette
 
Week3 final
Week3 finalWeek3 final
Week3 finaleducw200
 

Similar to Deep Learning: Session 2 how to architect (20)

2 day Deep Learning Workshop - Session 3
2 day Deep Learning Workshop - Session 3 2 day Deep Learning Workshop - Session 3
2 day Deep Learning Workshop - Session 3
 
Session 5 coding handson Tensorflow
Session 5 coding handson Tensorflow Session 5 coding handson Tensorflow
Session 5 coding handson Tensorflow
 
Deep Learning: Session 3 : How to succeed
Deep Learning: Session 3 : How to succeedDeep Learning: Session 3 : How to succeed
Deep Learning: Session 3 : How to succeed
 
Deep Learning Session 1 : bright future for you summary
Deep Learning Session 1 : bright future for you summaryDeep Learning Session 1 : bright future for you summary
Deep Learning Session 1 : bright future for you summary
 
2 day Deep Learning Workshop at Karunya - Session 2
2 day Deep Learning Workshop at Karunya - Session 22 day Deep Learning Workshop at Karunya - Session 2
2 day Deep Learning Workshop at Karunya - Session 2
 
Digital technology to generate save money gem conf cambridge 2014 reduced for...
Digital technology to generate save money gem conf cambridge 2014 reduced for...Digital technology to generate save money gem conf cambridge 2014 reduced for...
Digital technology to generate save money gem conf cambridge 2014 reduced for...
 
RSC SE Teaching toolkit no 8 Todaysmeet, QR codes and Slideshare - Jane Macke...
RSC SE Teaching toolkit no 8 Todaysmeet, QR codes and Slideshare - Jane Macke...RSC SE Teaching toolkit no 8 Todaysmeet, QR codes and Slideshare - Jane Macke...
RSC SE Teaching toolkit no 8 Todaysmeet, QR codes and Slideshare - Jane Macke...
 
DevLearn 2018 - Designing AR Experiences for Performance Support
DevLearn 2018 -  Designing AR Experiences for Performance SupportDevLearn 2018 -  Designing AR Experiences for Performance Support
DevLearn 2018 - Designing AR Experiences for Performance Support
 
MIT Deep Learning Basics: Introduction and Overview by Lex Fridman
MIT Deep Learning Basics: Introduction and Overview by Lex FridmanMIT Deep Learning Basics: Introduction and Overview by Lex Fridman
MIT Deep Learning Basics: Introduction and Overview by Lex Fridman
 
Sp12_Week3 complete
Sp12_Week3 completeSp12_Week3 complete
Sp12_Week3 complete
 
Building Innovative Products with Agile
Building Innovative Products with AgileBuilding Innovative Products with Agile
Building Innovative Products with Agile
 
Producing Online Educational Videos
Producing Online Educational VideosProducing Online Educational Videos
Producing Online Educational Videos
 
Improving WordPress Themes & Plugins Support Documentation
Improving WordPress Themes & Plugins Support DocumentationImproving WordPress Themes & Plugins Support Documentation
Improving WordPress Themes & Plugins Support Documentation
 
semester review
semester reviewsemester review
semester review
 
What is good design, from One Big Field
What is good design, from One Big FieldWhat is good design, from One Big Field
What is good design, from One Big Field
 
Flavours of SEO
Flavours of SEOFlavours of SEO
Flavours of SEO
 
Analytics For SEOs - Mozcation Portsmouth 11/7/12
Analytics For SEOs - Mozcation Portsmouth 11/7/12Analytics For SEOs - Mozcation Portsmouth 11/7/12
Analytics For SEOs - Mozcation Portsmouth 11/7/12
 
Lisa14 - Transforming to a Culture of Continuous Improvement
Lisa14 - Transforming to a Culture of Continuous ImprovementLisa14 - Transforming to a Culture of Continuous Improvement
Lisa14 - Transforming to a Culture of Continuous Improvement
 
CLSA Technology in Education and Leadership Activities Workshop
CLSA Technology in Education and Leadership Activities WorkshopCLSA Technology in Education and Leadership Activities Workshop
CLSA Technology in Education and Leadership Activities Workshop
 
Week3 final
Week3 finalWeek3 final
Week3 final
 

Recently uploaded

Specialize in a MSc within Biomanufacturing, and work part-time as Process En...
Specialize in a MSc within Biomanufacturing, and work part-time as Process En...Specialize in a MSc within Biomanufacturing, and work part-time as Process En...
Specialize in a MSc within Biomanufacturing, and work part-time as Process En...Juli Boned
 
Launch Your Research Career: A Beginner's Guide
Launch Your Research Career: A Beginner's GuideLaunch Your Research Career: A Beginner's Guide
Launch Your Research Career: A Beginner's GuideKaziFaisalAlam
 
Biography of Doctor Arif Patel Preston UK
Biography of Doctor Arif Patel Preston UKBiography of Doctor Arif Patel Preston UK
Biography of Doctor Arif Patel Preston UKArifPatel42
 
Mallu Aunts ℂall Girls Ahmedabad ℂall Us 6378878445 Top ℂlass ℂall Girl Servi...
Mallu Aunts ℂall Girls Ahmedabad ℂall Us 6378878445 Top ℂlass ℂall Girl Servi...Mallu Aunts ℂall Girls Ahmedabad ℂall Us 6378878445 Top ℂlass ℂall Girl Servi...
Mallu Aunts ℂall Girls Ahmedabad ℂall Us 6378878445 Top ℂlass ℂall Girl Servi...anjli garg#k09
 
Prest Reed Portfolio revamp Full Sail Presentation 2
Prest Reed Portfolio revamp Full Sail Presentation 2Prest Reed Portfolio revamp Full Sail Presentation 2
Prest Reed Portfolio revamp Full Sail Presentation 25203records
 
如何办理(USC毕业证书)南加利福尼亚大学毕业证成绩单本科硕士学位证留信学历认证
如何办理(USC毕业证书)南加利福尼亚大学毕业证成绩单本科硕士学位证留信学历认证如何办理(USC毕业证书)南加利福尼亚大学毕业证成绩单本科硕士学位证留信学历认证
如何办理(USC毕业证书)南加利福尼亚大学毕业证成绩单本科硕士学位证留信学历认证gakamzu
 
Crafting an effective CV for AYUSH Doctors.pdf
Crafting an effective CV for AYUSH Doctors.pdfCrafting an effective CV for AYUSH Doctors.pdf
Crafting an effective CV for AYUSH Doctors.pdfShri Dr Arul Selvan
 
Jual obat aborsi Dubai ( 085657271886 ) Cytote pil telat bulan penggugur kand...
Jual obat aborsi Dubai ( 085657271886 ) Cytote pil telat bulan penggugur kand...Jual obat aborsi Dubai ( 085657271886 ) Cytote pil telat bulan penggugur kand...
Jual obat aborsi Dubai ( 085657271886 ) Cytote pil telat bulan penggugur kand...ZurliaSoop
 
B.tech Civil Engineering Major Project by Deepak Kumar ppt.pdf
B.tech Civil Engineering Major Project by Deepak Kumar ppt.pdfB.tech Civil Engineering Major Project by Deepak Kumar ppt.pdf
B.tech Civil Engineering Major Project by Deepak Kumar ppt.pdfDeepak15CivilEngg
 
Ascension Brown - Internship Resume 2024
Ascension Brown -  Internship Resume 2024Ascension Brown -  Internship Resume 2024
Ascension Brown - Internship Resume 2024ascensionbrown
 
Career counseling presentation for commerce students
Career counseling presentation for commerce studentsCareer counseling presentation for commerce students
Career counseling presentation for commerce studentsHarmanDhillon43
 
TEST BANK For Growth and Development Across the Lifespan, 3rd Edition By Glor...
TEST BANK For Growth and Development Across the Lifespan, 3rd Edition By Glor...TEST BANK For Growth and Development Across the Lifespan, 3rd Edition By Glor...
TEST BANK For Growth and Development Across the Lifespan, 3rd Edition By Glor...rightmanforbloodline
 
K Venkat Naveen Kumar | GCP Data Engineer | CV
K Venkat Naveen Kumar | GCP Data Engineer | CVK Venkat Naveen Kumar | GCP Data Engineer | CV
K Venkat Naveen Kumar | GCP Data Engineer | CVK VENKAT NAVEEN KUMAR
 
Fracture design PowerPoint presentations
Fracture design PowerPoint presentationsFracture design PowerPoint presentations
Fracture design PowerPoint presentationsjitiniift
 
b-sc-agri-course-curriculum.pdf for Karnataka state board
b-sc-agri-course-curriculum.pdf for Karnataka state boardb-sc-agri-course-curriculum.pdf for Karnataka state board
b-sc-agri-course-curriculum.pdf for Karnataka state boardramyaul734
 
LinkedIn For Job Search Presentation May 2024
LinkedIn For Job Search Presentation May 2024LinkedIn For Job Search Presentation May 2024
LinkedIn For Job Search Presentation May 2024Bruce Bennett
 
obat aborsi gresik wa 081336238223 jual obat aborsi cytotec asli di gresik782...
obat aborsi gresik wa 081336238223 jual obat aborsi cytotec asli di gresik782...obat aborsi gresik wa 081336238223 jual obat aborsi cytotec asli di gresik782...
obat aborsi gresik wa 081336238223 jual obat aborsi cytotec asli di gresik782...yulianti213969
 
We’re looking for a Technology consultant to join our Team!
We’re looking for a Technology consultant to join our Team!We’re looking for a Technology consultant to join our Team!
We’re looking for a Technology consultant to join our Team!Juli Boned
 
Sales Experience Presentation - Angel Lopez
Sales Experience Presentation - Angel LopezSales Experience Presentation - Angel Lopez
Sales Experience Presentation - Angel LopezInfinity Skies Corp
 

Recently uploaded (20)

Specialize in a MSc within Biomanufacturing, and work part-time as Process En...
Specialize in a MSc within Biomanufacturing, and work part-time as Process En...Specialize in a MSc within Biomanufacturing, and work part-time as Process En...
Specialize in a MSc within Biomanufacturing, and work part-time as Process En...
 
Launch Your Research Career: A Beginner's Guide
Launch Your Research Career: A Beginner's GuideLaunch Your Research Career: A Beginner's Guide
Launch Your Research Career: A Beginner's Guide
 
Biography of Doctor Arif Patel Preston UK
Biography of Doctor Arif Patel Preston UKBiography of Doctor Arif Patel Preston UK
Biography of Doctor Arif Patel Preston UK
 
Mallu Aunts ℂall Girls Ahmedabad ℂall Us 6378878445 Top ℂlass ℂall Girl Servi...
Mallu Aunts ℂall Girls Ahmedabad ℂall Us 6378878445 Top ℂlass ℂall Girl Servi...Mallu Aunts ℂall Girls Ahmedabad ℂall Us 6378878445 Top ℂlass ℂall Girl Servi...
Mallu Aunts ℂall Girls Ahmedabad ℂall Us 6378878445 Top ℂlass ℂall Girl Servi...
 
Prest Reed Portfolio revamp Full Sail Presentation 2
Prest Reed Portfolio revamp Full Sail Presentation 2Prest Reed Portfolio revamp Full Sail Presentation 2
Prest Reed Portfolio revamp Full Sail Presentation 2
 
Cara Gugurkan Kandungan Awal Kehamilan 1 bulan (087776558899)
Cara Gugurkan Kandungan Awal Kehamilan 1 bulan (087776558899)Cara Gugurkan Kandungan Awal Kehamilan 1 bulan (087776558899)
Cara Gugurkan Kandungan Awal Kehamilan 1 bulan (087776558899)
 
如何办理(USC毕业证书)南加利福尼亚大学毕业证成绩单本科硕士学位证留信学历认证
如何办理(USC毕业证书)南加利福尼亚大学毕业证成绩单本科硕士学位证留信学历认证如何办理(USC毕业证书)南加利福尼亚大学毕业证成绩单本科硕士学位证留信学历认证
如何办理(USC毕业证书)南加利福尼亚大学毕业证成绩单本科硕士学位证留信学历认证
 
Crafting an effective CV for AYUSH Doctors.pdf
Crafting an effective CV for AYUSH Doctors.pdfCrafting an effective CV for AYUSH Doctors.pdf
Crafting an effective CV for AYUSH Doctors.pdf
 
Jual obat aborsi Dubai ( 085657271886 ) Cytote pil telat bulan penggugur kand...
Jual obat aborsi Dubai ( 085657271886 ) Cytote pil telat bulan penggugur kand...Jual obat aborsi Dubai ( 085657271886 ) Cytote pil telat bulan penggugur kand...
Jual obat aborsi Dubai ( 085657271886 ) Cytote pil telat bulan penggugur kand...
 
B.tech Civil Engineering Major Project by Deepak Kumar ppt.pdf
B.tech Civil Engineering Major Project by Deepak Kumar ppt.pdfB.tech Civil Engineering Major Project by Deepak Kumar ppt.pdf
B.tech Civil Engineering Major Project by Deepak Kumar ppt.pdf
 
Ascension Brown - Internship Resume 2024
Ascension Brown -  Internship Resume 2024Ascension Brown -  Internship Resume 2024
Ascension Brown - Internship Resume 2024
 
Career counseling presentation for commerce students
Career counseling presentation for commerce studentsCareer counseling presentation for commerce students
Career counseling presentation for commerce students
 
TEST BANK For Growth and Development Across the Lifespan, 3rd Edition By Glor...
TEST BANK For Growth and Development Across the Lifespan, 3rd Edition By Glor...TEST BANK For Growth and Development Across the Lifespan, 3rd Edition By Glor...
TEST BANK For Growth and Development Across the Lifespan, 3rd Edition By Glor...
 
K Venkat Naveen Kumar | GCP Data Engineer | CV
K Venkat Naveen Kumar | GCP Data Engineer | CVK Venkat Naveen Kumar | GCP Data Engineer | CV
K Venkat Naveen Kumar | GCP Data Engineer | CV
 
Fracture design PowerPoint presentations
Fracture design PowerPoint presentationsFracture design PowerPoint presentations
Fracture design PowerPoint presentations
 
b-sc-agri-course-curriculum.pdf for Karnataka state board
b-sc-agri-course-curriculum.pdf for Karnataka state boardb-sc-agri-course-curriculum.pdf for Karnataka state board
b-sc-agri-course-curriculum.pdf for Karnataka state board
 
LinkedIn For Job Search Presentation May 2024
LinkedIn For Job Search Presentation May 2024LinkedIn For Job Search Presentation May 2024
LinkedIn For Job Search Presentation May 2024
 
obat aborsi gresik wa 081336238223 jual obat aborsi cytotec asli di gresik782...
obat aborsi gresik wa 081336238223 jual obat aborsi cytotec asli di gresik782...obat aborsi gresik wa 081336238223 jual obat aborsi cytotec asli di gresik782...
obat aborsi gresik wa 081336238223 jual obat aborsi cytotec asli di gresik782...
 
We’re looking for a Technology consultant to join our Team!
We’re looking for a Technology consultant to join our Team!We’re looking for a Technology consultant to join our Team!
We’re looking for a Technology consultant to join our Team!
 
Sales Experience Presentation - Angel Lopez
Sales Experience Presentation - Angel LopezSales Experience Presentation - Angel Lopez
Sales Experience Presentation - Angel Lopez
 

Deep Learning: Session 2 how to architect

  • 1. Design How to solve a problem using Deep Learning AI for Good Workshop July 2019 Session 3 https://sites.google.com/view/AIforEveryone
  • 2. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Key Learning objective for Day 1 How to solve a problem with Deep Learning ? How to design an neural network architecture?
  • 3. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Quiz #1 Is it possible to map hand signs for deaf  speech  Hand signs   Speech
  • 4. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone A B •
  • 5. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Quiz #2 Is it possible to “see the depth” for visual impaired  Yes / no ?
  • 6. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Quiz #2 Is it possible to feel the depth for visual impaired
  • 7. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
  • 8. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Topics in this presentation •New way to think from today ! • How to use Deep Learning to solve any problem • How to model & architect Neural Networks
  • 9. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone New way to think from today !
  • 10. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone New way to think from today !
  • 11. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Deep Learning idea-a-thon: How to solve a problem by designing novel neural network architectures? CNN RNN Fully Connected Merge CNN is suitable architecture to extract features out of any data that has spatial relationships. For example, An photo image spatial info..or info spread across space In general, a recurrent neural network could be considered as the best neural network model for extracting features out of temporal data. A temporal data is basically a data that varies over time such as ECG, music, speech, sentences, words. LSTM is a advanced RNN To classify / predict To combine the learnings of two neural networks. (to combine the power of 2 people’s brains) Attention To learn to focus on the most important aspects to achieve a particular task Generative Deep Learning To model creative tasks as to compose a music or to come up a painting
  • 12. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Our inspiration / acknowledgements Friendly approaches : 1) KERAS.io François Chollet’s Book on “Deep Learning with Python” 2) Deeplearning.ai (Coursera.org) Andrew Ng 3) Udacity Deep Learning Free course 4) Google Machine Learning Course https://developers.google.com/machine-learning/crash-course/
  • 13. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone More inspiration/ acknowledgements Excellent Resources • Stanford cs231 n http://cs231n.stanford.edu • MIT Deep Learning http://introtodeeplearning.com/ https://deeplearning.mit.edu • IIT Madras my classes notes with Prof. Anurag (Deep Learning)
  • 14. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Message: Using Representation learning to learn to represent A as B
  • 15. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Learning objective: How did the magic happen? Deep Learning
  • 16. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Learning objective: How did the magic happen?
  • 17. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
  • 18. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Learn to map Xy • Examples of x, y
  • 19. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone A  B
  • 20. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
  • 21. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
  • 22. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone
  • 23. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Fun activity
  • 24. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Learning objective: How do solve a problem using Deep Learning? Case study: self driving car
  • 25. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Camera view ? steering angle • Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car Credits: Nvidia
  • 26. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone •
  • 27. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Learn to map x->y
  • 28. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone What is the function to map x->y •
  • 29. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Key Learning objective for Day 1 How to solve a problem with Deep Learning ? How to design an neural network architecture?
  • 30. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Architecture patterns Neural Network Design Pattern #1 classification problems CNN Fully Connected Prediction of what of objects is in this photo
  • 31. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #1 CNN Fully Connected Turn car left Turn car right Don’t Turn the car
  • 32. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #1
  • 33. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #1
  • 34. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Architecture patterns Neural Network Design Pattern #2 Regression problems CNN Fully Connected Continuous number
  • 35. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #2 Regression problems CNN Fully Connected Turn the car by 10 degrees
  • 36. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #2 Regression problems
  • 37. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #2 Regression problems •
  • 38. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Architecture patterns Neural Network Design Pattern #3 multimodal classification CNN Fully Connected Predicted class RNN Merge
  • 39. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Architecture patterns Neural Network Design Pattern #3 multimodal classification
  • 40. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Architecture patterns Neural Network Design Pattern #3 multimodal classification
  • 41. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Quiz Neural Network Design Pattern #3 multimodal classification • Quiz: What was x and y in the problem?
  • 42. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Quiz Neural Network Design Pattern #3 • Quiz: What was x and y in the problem?
  • 43. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Quiz multimodal classification
  • 44. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Answering Visual Questions from Blind People
  • 45. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #3 multimodal classification
  • 46. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Architecture patterns Neural Network Design Pattern #3 multimodal classification •
  • 47. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #3
  • 48. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Architecture patterns Neural Network Design Pattern #4 video question answering CNN Fully Connected Predicted class RNN Merge Video Question
  • 49. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Architecture patterns Neural Network Design Pattern #4 video question answering
  • 50. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #4 video question answering •
  • 51. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #4 video question answering
  • 52. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #4 video question answering
  • 53. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #4 video question answering
  • 54. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #4 video question answering
  • 55. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #4 video question answering
  • 56. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Architecture patterns Neural Network Design Pattern #5 image question answering CNN Answer (text) RNN Merge Image (photo) Question (text) RNN
  • 57. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #5 image question answering
  • 58. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Architecture patterns Neural Network Design Pattern #6
  • 59. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #6
  • 60. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Architecture patterns Neural Network Design Pattern #7 image to image translation CNN Image (text) Image (photo) CNN Features of the image
  • 61. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #7 image to image translation
  • 62. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #7 image to image translation
  • 63. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #7 image to image translation
  • 64. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Neural Network Design Pattern #7 image to image translation
  • 65. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Quiz Can a neural network output 2 types of output? • How to architect Multi output network?
  • 66. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Quiz Multi output network
  • 67. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Quiz how to extract features from multiple sources ? • I have a input of audio and video and text. How to combine the features from all 3?
  • 68. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Quiz how to extract features from multiple sources ?
  • 69. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone What did you learn? (Day 1) How to solve a problem with Deep Learning ? How to design an neural network architecture?
  • 70. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Key ideas to remember You can map any thing to anything with Deep Learning AB • Anything  Machine Learns to map  Anything
  • 71. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Key ideas to remember How to design a architectures to handle various types of A  B How to design this architecture? CNN / RNN ? Fully Connected or RNN ? Predicted class RNN / Fully connected ? Merge / Attention ? Video Question A  --------------------------------------------------------------------------------------------------------------------------  B
  • 72. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Key ideas to remember From architecture to code ? (just learn early glimpse of how code looks like.) Just 1 page of code is enough for a complex problems such as video question answering
  • 73. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Key ideas to remember If you didn’t understand the code*, just don’t worry. • Why not to worry? • Solving the video question answering problem was not possible until 2017. • To solve this problem, it required dozens of experts in Google lab to dedicate 6 months of effort! *code = code in the previous slide
  • 74. Acknowledgments & Credits are mentioned to inspirational resources presented in the end of presentation. For more like this, https://sites.google.com/view/AIforEveryone Team activity idea-a-ton Goal of this thinking activity How to solve a problem with Deep Learning ? How to design an neural network architecture?