SlideShare a Scribd company logo
1 of 68
Download to read offline
1.1 Integrating AI techniques to build meaningful product concepts 1
CONFIDENTIAL Template Innovation Day 2018CONFIDENTIAL
INTEGRATING AI TECHNIQUES TO BUILD
MEANINGFUL PRODUCT CONCEPTS
Jochem Grietens
System engineer – A.I. passionate
jochem.grietens@verhaert.com
TRACK 1 - CIRCULAR ECONOMY FOR A BETTER WORLD
1.1 Integrating AI techniques to build meaningful product concepts 2
CONFIDENTIAL
Introduction
1.1 Integrating AI techniques to build meaningful product concepts 3
CONFIDENTIAL
1. Introduction
2. A recycling use case: Hackathon
3. Machine learning: What does it mean to “see” ?
4. How does a machine “see” ?
Content
1.1 Integrating AI techniques to build meaningful product concepts 4
CONFIDENTIAL
“Fail fast, fail cheap, learn faster”
Understanding comes from running through the cycle.
Rapid prototyping credo
1.1 Integrating AI techniques to build meaningful product concepts 5
CONFIDENTIAL
A recycling use case
Load Hackathon Case
1.1 Integrating AI techniques to build meaningful product concepts 6
CONFIDENTIAL
aaa
Load hackathon 2018
• Theme A: Help The Community
• Theme B: Change behavior
• aim for a sustainable world
• live a healthier life
• become a better citizen
1.1 Integrating AI techniques to build meaningful product concepts 7
CONFIDENTIAL
1.1 Integrating AI techniques to build meaningful product concepts 8
CONFIDENTIAL
1. Business understanding
Hackathon process
1.1 Integrating AI techniques to build meaningful product concepts 9
CONFIDENTIAL
Closing the loop in a circular economy
Challenges for companies:
• Little incentive to close the loop
• Companies have no control over the downstream process.
Business understanding
1.1 Integrating AI techniques to build meaningful product concepts 10
CONFIDENTIAL
Sorting is hard
Sorting is boring
Sorting is a community effort
yellow for plastic and metal blue for paper green for glass
Business understanding
1.1 Integrating AI techniques to build meaningful product concepts 11
CONFIDENTIAL
Concept generation
1.1 Integrating AI techniques to build meaningful product concepts 12
CONFIDENTIAL
3. Data understanding
4. Data preparation
5. Modeling/app building
Hackathon process
1.1 Integrating AI techniques to build meaningful product concepts 13
CONFIDENTIAL
1.1 Integrating AI techniques to build meaningful product concepts 14
CONFIDENTIAL
Goals
Help people sort
Fun and engaging
Create a community
Help close the circular economy loop.
1.1 Integrating AI techniques to build meaningful product concepts 15
CONFIDENTIAL
1.1 Integrating AI techniques to build meaningful product concepts 16
CONFIDENTIAL
1.1 Integrating AI techniques to build meaningful product concepts 17
CONFIDENTIAL
1.1 Integrating AI techniques to build meaningful product concepts 18
CONFIDENTIAL
1.1 Integrating AI techniques to build meaningful product concepts 19
CONFIDENTIAL
Hackathon process
6 Evaluation
7 Deployment
1.1 Integrating AI techniques to build meaningful product concepts 20
CONFIDENTIAL
Architecture
1.1 Integrating AI techniques to build meaningful product concepts 21
CONFIDENTIAL
Machine learning model
What does it mean to “see”
1.1 Integrating AI techniques to build meaningful product concepts 22
CONFIDENTIAL
What does it mean to “see”
Primate visual system
1.1 Integrating AI techniques to build meaningful product concepts 23
CONFIDENTIAL
What does it mean to “see”
1.1 Integrating AI techniques to build meaningful product concepts 24
CONFIDENTIAL
“Seeing”:
• Recognizing (=classification)
• Localization
• Segmentation
• Understanding
What does it mean to “see”
1.1 Integrating AI techniques to build meaningful product concepts 25
CONFIDENTIAL
Neural network to fit our goal
1.1 Integrating AI techniques to build meaningful product concepts 26
CONFIDENTIAL
How does a machine “see” ?
1.1 Integrating AI techniques to build meaningful product concepts 27
CONFIDENTIAL
Neural network
1.1 Integrating AI techniques to build meaningful product concepts 28
CONFIDENTIAL
Neural network
yellow for plastic and metal
blue for paper
green for glass
1.1 Integrating AI techniques to build meaningful product concepts 29
CONFIDENTIAL
1. Input Encoding
Neural network
1.1 Integrating AI techniques to build meaningful product concepts 30
CONFIDENTIAL
Input Encoding
Picture = 3 arrays of numbers
Neural network
R
G
B
1.1 Integrating AI techniques to build meaningful product concepts 31
CONFIDENTIAL
Output encoding
1. metal  ( 1 0 0 )
2. paper  ( 0 1 0 )
3. Glass  ( 0 0 1 )
Neural network
1.1 Integrating AI techniques to build meaningful product concepts 32
CONFIDENTIAL
Neural network
( 1 0 0 )
( 0 1 0 )
( 0 0 1 )
1.1 Integrating AI techniques to build meaningful product concepts 33
CONFIDENTIAL
The neuron
Neural network
1.1 Integrating AI techniques to build meaningful product concepts 34
CONFIDENTIAL
Neural network
1.1 Integrating AI techniques to build meaningful product concepts 35
CONFIDENTIAL
Neural network
1.1 Integrating AI techniques to build meaningful product concepts 36
CONFIDENTIAL
Neural network
1.1 Integrating AI techniques to build meaningful product concepts 37
CONFIDENTIAL
Convolutional neural network
Conv. neural networkInput
Output
0,9
0,1
0
yellow for plastic and metal blue for paper green for glass
1.1 Integrating AI techniques to build meaningful product concepts 38
CONFIDENTIAL
Neural network training
Forward pass
1.1 Integrating AI techniques to build meaningful product concepts 39
CONFIDENTIAL
Neural network training
0,9
0,1
0
Prediction
1.1 Integrating AI techniques to build meaningful product concepts 40
CONFIDENTIAL
Neural network training
0,9
0,1
0
Prediction
1
0
0
Truth
COMPARE
1.1 Integrating AI techniques to build meaningful product concepts 41
CONFIDENTIAL
Prediction Truth
Calculate the error
Neural network training
0,9
0,1
0
1
0
0
1.1 Integrating AI techniques to build meaningful product concepts 42
CONFIDENTIAL
Neural network training
Backwards pass
Prediction Truth
0,9
0,1
0
1
0
0
1.1 Integrating AI techniques to build meaningful product concepts 43
CONFIDENTIAL
Many layers stacked
Deep neural network
1.1 Integrating AI techniques to build meaningful product concepts 44
CONFIDENTIAL
Specific WIRING of the first regions for image recognition
Deep convolutional neural network
1.1 Integrating AI techniques to build meaningful product concepts 45
CONFIDENTIAL
• Convolution
• Fully connected
Convolutional neural network
1.1 Integrating AI techniques to build meaningful product concepts 46
CONFIDENTIAL
Convolution = comparing to patterns
Convolution
1.1 Integrating AI techniques to build meaningful product concepts 47
CONFIDENTIAL
=6600
Convolution
Feature learning
Great match
1.1 Integrating AI techniques to build meaningful product concepts 48
CONFIDENTIAL
= 0
Convolution
Convolution
Bad match
1.1 Integrating AI techniques to build meaningful product concepts 49
CONFIDENTIAL
Feature maps
1.1 Integrating AI techniques to build meaningful product concepts 50
CONFIDENTIAL
Neural network LEARNS the features from examples
Convolutional neural network
1.1 Integrating AI techniques to build meaningful product concepts 51
CONFIDENTIAL
Neural network LEARNS the features from examples
Convolutional neural network
1.1 Integrating AI techniques to build meaningful product concepts 52
CONFIDENTIAL
Convolutional network
1.1 Integrating AI techniques to build meaningful product concepts 53
CONFIDENTIAL
Flattening
1.1 Integrating AI techniques to build meaningful product concepts 54
CONFIDENTIAL
Flattening
1.1 Integrating AI techniques to build meaningful product concepts 55
CONFIDENTIAL
Classification
1.1 Integrating AI techniques to build meaningful product concepts 56
CONFIDENTIAL
Classification
0
1
Tesla
Volkswagen
One Hot encoding:
1
0
0
1
Tesla
0,2
0,8
1.1 Integrating AI techniques to build meaningful product concepts 57
CONFIDENTIAL
Convolutional neural network
1.1 Integrating AI techniques to build meaningful product concepts 58
CONFIDENTIAL
TrashNet dataset : to train on 2527 labeled images
Way too little to learn a deep neural net “to see” AND “to recognize”
Training data
1.1 Integrating AI techniques to build meaningful product concepts 59
CONFIDENTIAL
Convolutional neural network
Transfer learning = Learning to see on a different dataset.
1.1 Integrating AI techniques to build meaningful product concepts 60
CONFIDENTIAL
Can we learn how to see on Cifar dataset:
60,000 32x32 color images in 10 different classes.
Learn how to recognize on the trashnet database
Transfer learning
1.1 Integrating AI techniques to build meaningful product concepts 61
CONFIDENTIAL
Transfer learning
Freeze Finetune
1.1 Integrating AI techniques to build meaningful product concepts 62
CONFIDENTIAL
Learning by heart vs. learning general features
Algorithm should have learned general features :
• Visual effects of metallic light reflection
• Can shape features
• Size vs environment
• …
Instead it learned:
Very specific features, like the shadow on the hand …
Overtraining
 MODEL DOES NOT GENERALIZE WELL
1.1 Integrating AI techniques to build meaningful product concepts 63
CONFIDENTIAL
Central ML problem
Performance on new data ?
Test it!
How to detect overfitting
Training and tuning the
models.
Check performance
during development.
Don’t touch until the very
end.
1.1 Integrating AI techniques to build meaningful product concepts 64
CONFIDENTIAL
Detecting overfitting
“Performance training set >> test set  likely overfitting.”
Dealing with overfitting
1.1 Integrating AI techniques to build meaningful product concepts 65
CONFIDENTIAL
More data - Data augmentation
Dealing with overtraining
1.1 Integrating AI techniques to build meaningful product concepts 66
CONFIDENTIAL
Dealing with overtraining
X1 X2
1.1 Integrating AI techniques to build meaningful product concepts 67
CONFIDENTIAL
Achieved
• 70% accuracy on test set.
• 65% in real world validation.
Results
1.1 Integrating AI techniques to build meaningful product concepts 68
CONFIDENTIAL
One group, five brands
Our services are marketed through 5 brands each
addressing specific missions in product development.
INTEGRATED PRODUCT DEVELOPMENT
ON-SITE
PRODUCT
DEVELOPMENT
DIGITAL
PRODUCTS
DEVELOPMENT
OPTICAL
PRODUCTS
DEVELOPMENT
VENTURING

More Related Content

What's hot

Security by default - Building continuous cyber-resilience.
Security by default - Building continuous cyber-resilience.Security by default - Building continuous cyber-resilience.
Security by default - Building continuous cyber-resilience.Thoughtworks
 
Martin Charlier - Designing Connected Products - raincloud.eu
Martin Charlier - Designing Connected Products - raincloud.eu Martin Charlier - Designing Connected Products - raincloud.eu
Martin Charlier - Designing Connected Products - raincloud.eu Business of Software Conference
 
Smart City StarterK!t at Beyond Data Event 2018
Smart City StarterK!t at Beyond Data Event 2018Smart City StarterK!t at Beyond Data Event 2018
Smart City StarterK!t at Beyond Data Event 2018Venturespring
 
User-Modifiable Software: Smalltalk and HyperCard
User-Modifiable Software: Smalltalk and HyperCardUser-Modifiable Software: Smalltalk and HyperCard
User-Modifiable Software: Smalltalk and HyperCardJosh Justice
 
Innovating Enterprise Innovation Processes
Innovating Enterprise Innovation Processes Innovating Enterprise Innovation Processes
Innovating Enterprise Innovation Processes Massimo Canducci
 
Developer's Introduction to Machine Learning
Developer's Introduction to Machine LearningDeveloper's Introduction to Machine Learning
Developer's Introduction to Machine LearningChristopher Mohritz
 
Systematic Innovation in Software Using TRIZ
Systematic Innovation in Software Using TRIZSystematic Innovation in Software Using TRIZ
Systematic Innovation in Software Using TRIZMichael Kalika
 

What's hot (9)

Security by default - Building continuous cyber-resilience.
Security by default - Building continuous cyber-resilience.Security by default - Building continuous cyber-resilience.
Security by default - Building continuous cyber-resilience.
 
Martin Charlier - Designing Connected Products - raincloud.eu
Martin Charlier - Designing Connected Products - raincloud.eu Martin Charlier - Designing Connected Products - raincloud.eu
Martin Charlier - Designing Connected Products - raincloud.eu
 
R&D as a service
R&D as a serviceR&D as a service
R&D as a service
 
Connected Product Experiences
Connected Product ExperiencesConnected Product Experiences
Connected Product Experiences
 
Smart City StarterK!t at Beyond Data Event 2018
Smart City StarterK!t at Beyond Data Event 2018Smart City StarterK!t at Beyond Data Event 2018
Smart City StarterK!t at Beyond Data Event 2018
 
User-Modifiable Software: Smalltalk and HyperCard
User-Modifiable Software: Smalltalk and HyperCardUser-Modifiable Software: Smalltalk and HyperCard
User-Modifiable Software: Smalltalk and HyperCard
 
Innovating Enterprise Innovation Processes
Innovating Enterprise Innovation Processes Innovating Enterprise Innovation Processes
Innovating Enterprise Innovation Processes
 
Developer's Introduction to Machine Learning
Developer's Introduction to Machine LearningDeveloper's Introduction to Machine Learning
Developer's Introduction to Machine Learning
 
Systematic Innovation in Software Using TRIZ
Systematic Innovation in Software Using TRIZSystematic Innovation in Software Using TRIZ
Systematic Innovation in Software Using TRIZ
 

Similar to Integrating AI techniques to build meaningful product concepts (by Jochem Grietens)

The acceleration of Artificial Intelligence (by Jochem Grietens)
The acceleration of Artificial Intelligence (by Jochem Grietens)The acceleration of Artificial Intelligence (by Jochem Grietens)
The acceleration of Artificial Intelligence (by Jochem Grietens)Verhaert Masters in Innovation
 
Designing Connected Products - Web Directions 2015 Sydney
Designing Connected Products - Web Directions 2015 SydneyDesigning Connected Products - Web Directions 2015 Sydney
Designing Connected Products - Web Directions 2015 SydneyMartin Charlier
 
"Bringing Computer Vision to the Consumer," a Keynote Presentation from Dyson
"Bringing Computer Vision to the Consumer," a Keynote Presentation from Dyson"Bringing Computer Vision to the Consumer," a Keynote Presentation from Dyson
"Bringing Computer Vision to the Consumer," a Keynote Presentation from DysonEdge AI and Vision Alliance
 
Virtual Reality in AEC
Virtual Reality in AECVirtual Reality in AEC
Virtual Reality in AECTero Järvinen
 
BESPOKE OFFICE INTERIOR DESIGNERS IN INDIA
BESPOKE OFFICE INTERIOR DESIGNERS IN INDIABESPOKE OFFICE INTERIOR DESIGNERS IN INDIA
BESPOKE OFFICE INTERIOR DESIGNERS IN INDIAsiriajadhav29
 
What makes a Strong Engineering Culture
What makes a Strong Engineering Culture What makes a Strong Engineering Culture
What makes a Strong Engineering Culture Michael Kalika
 
3D simulations as an innovation tool
3D simulations as an innovation tool3D simulations as an innovation tool
3D simulations as an innovation toolMattia Crespi
 
The Maker Movement by @boardofinno
The Maker Movement by @boardofinnoThe Maker Movement by @boardofinno
The Maker Movement by @boardofinnoBoard of Innovation
 
Foundational Elements for IoT (1)
Foundational Elements for IoT (1)Foundational Elements for IoT (1)
Foundational Elements for IoT (1)Nicolas Delorme
 
Crafting a central product narrative
Crafting a central product narrativeCrafting a central product narrative
Crafting a central product narrativeAlex Pandel
 
UX STRAT Online 2021 Presentation by Mike Kuniavsky, Accenture
UX STRAT Online 2021 Presentation by Mike Kuniavsky, AccentureUX STRAT Online 2021 Presentation by Mike Kuniavsky, Accenture
UX STRAT Online 2021 Presentation by Mike Kuniavsky, AccentureUX STRAT
 
Applying design thinking to IoT
Applying design thinking to IoTApplying design thinking to IoT
Applying design thinking to IoTEli Otniel Garcia
 
Accelerating the Packaging Design Process with Artificial Intelligence
Accelerating the Packaging Design Process with Artificial IntelligenceAccelerating the Packaging Design Process with Artificial Intelligence
Accelerating the Packaging Design Process with Artificial IntelligenceNuxeo
 
End-to-End AI Acceleration with Intel
End-to-End AI Acceleration with IntelEnd-to-End AI Acceleration with Intel
End-to-End AI Acceleration with IntelADTELLIGENCE GmbH
 
IoTforReal Seminar slidedeck
IoTforReal Seminar slidedeckIoTforReal Seminar slidedeck
IoTforReal Seminar slidedeckCodit
 
Microcontrollers for Artificial Intelligence and Machine Learning
Microcontrollers for Artificial Intelligence and Machine LearningMicrocontrollers for Artificial Intelligence and Machine Learning
Microcontrollers for Artificial Intelligence and Machine LearningIRJET Journal
 

Similar to Integrating AI techniques to build meaningful product concepts (by Jochem Grietens) (20)

The acceleration of Artificial Intelligence (by Jochem Grietens)
The acceleration of Artificial Intelligence (by Jochem Grietens)The acceleration of Artificial Intelligence (by Jochem Grietens)
The acceleration of Artificial Intelligence (by Jochem Grietens)
 
Designing Connected Products - Web Directions 2015 Sydney
Designing Connected Products - Web Directions 2015 SydneyDesigning Connected Products - Web Directions 2015 Sydney
Designing Connected Products - Web Directions 2015 Sydney
 
"Bringing Computer Vision to the Consumer," a Keynote Presentation from Dyson
"Bringing Computer Vision to the Consumer," a Keynote Presentation from Dyson"Bringing Computer Vision to the Consumer," a Keynote Presentation from Dyson
"Bringing Computer Vision to the Consumer," a Keynote Presentation from Dyson
 
Virtual Reality in AEC
Virtual Reality in AECVirtual Reality in AEC
Virtual Reality in AEC
 
Innovation & Frameworks
Innovation & FrameworksInnovation & Frameworks
Innovation & Frameworks
 
Conversational user interfaces (by Jochem Grietens)
Conversational user interfaces (by Jochem Grietens)Conversational user interfaces (by Jochem Grietens)
Conversational user interfaces (by Jochem Grietens)
 
BESPOKE OFFICE INTERIOR DESIGNERS IN INDIA
BESPOKE OFFICE INTERIOR DESIGNERS IN INDIABESPOKE OFFICE INTERIOR DESIGNERS IN INDIA
BESPOKE OFFICE INTERIOR DESIGNERS IN INDIA
 
Practical uses of AI in retail
Practical uses of AI in retailPractical uses of AI in retail
Practical uses of AI in retail
 
What makes a Strong Engineering Culture
What makes a Strong Engineering Culture What makes a Strong Engineering Culture
What makes a Strong Engineering Culture
 
3D simulations as an innovation tool
3D simulations as an innovation tool3D simulations as an innovation tool
3D simulations as an innovation tool
 
The Maker Movement by @boardofinno
The Maker Movement by @boardofinnoThe Maker Movement by @boardofinno
The Maker Movement by @boardofinno
 
Foundational Elements for IoT (1)
Foundational Elements for IoT (1)Foundational Elements for IoT (1)
Foundational Elements for IoT (1)
 
Crafting a central product narrative
Crafting a central product narrativeCrafting a central product narrative
Crafting a central product narrative
 
UX STRAT Online 2021 Presentation by Mike Kuniavsky, Accenture
UX STRAT Online 2021 Presentation by Mike Kuniavsky, AccentureUX STRAT Online 2021 Presentation by Mike Kuniavsky, Accenture
UX STRAT Online 2021 Presentation by Mike Kuniavsky, Accenture
 
Applying design thinking to IoT
Applying design thinking to IoTApplying design thinking to IoT
Applying design thinking to IoT
 
The 10 most innovative cognitive solution providers 2018
The 10 most innovative cognitive solution providers 2018The 10 most innovative cognitive solution providers 2018
The 10 most innovative cognitive solution providers 2018
 
Accelerating the Packaging Design Process with Artificial Intelligence
Accelerating the Packaging Design Process with Artificial IntelligenceAccelerating the Packaging Design Process with Artificial Intelligence
Accelerating the Packaging Design Process with Artificial Intelligence
 
End-to-End AI Acceleration with Intel
End-to-End AI Acceleration with IntelEnd-to-End AI Acceleration with Intel
End-to-End AI Acceleration with Intel
 
IoTforReal Seminar slidedeck
IoTforReal Seminar slidedeckIoTforReal Seminar slidedeck
IoTforReal Seminar slidedeck
 
Microcontrollers for Artificial Intelligence and Machine Learning
Microcontrollers for Artificial Intelligence and Machine LearningMicrocontrollers for Artificial Intelligence and Machine Learning
Microcontrollers for Artificial Intelligence and Machine Learning
 

More from Verhaert Masters in Innovation

Software language over the last 50 years, what will be next (by Pieter Zulian...
Software language over the last 50 years, what will be next (by Pieter Zulian...Software language over the last 50 years, what will be next (by Pieter Zulian...
Software language over the last 50 years, what will be next (by Pieter Zulian...Verhaert Masters in Innovation
 
Geospatial technologies, the evolution and impact on our daily life (by Nicol...
Geospatial technologies, the evolution and impact on our daily life (by Nicol...Geospatial technologies, the evolution and impact on our daily life (by Nicol...
Geospatial technologies, the evolution and impact on our daily life (by Nicol...Verhaert Masters in Innovation
 
Advanced human interfaces, the underestimated enabler for innovation (by Bert...
Advanced human interfaces, the underestimated enabler for innovation (by Bert...Advanced human interfaces, the underestimated enabler for innovation (by Bert...
Advanced human interfaces, the underestimated enabler for innovation (by Bert...Verhaert Masters in Innovation
 
The first humanoid robot, wabot 1 (by Robrecht Van Velthoven)
The first humanoid robot, wabot 1 (by Robrecht Van Velthoven)The first humanoid robot, wabot 1 (by Robrecht Van Velthoven)
The first humanoid robot, wabot 1 (by Robrecht Van Velthoven)Verhaert Masters in Innovation
 
The government as launching customer, a great opportunity for companies (by R...
The government as launching customer, a great opportunity for companies (by R...The government as launching customer, a great opportunity for companies (by R...
The government as launching customer, a great opportunity for companies (by R...Verhaert Masters in Innovation
 
Landing on the moon, the impact and future opportunities (by Sam Waes)
Landing on the moon, the impact and future opportunities (by Sam Waes)Landing on the moon, the impact and future opportunities (by Sam Waes)
Landing on the moon, the impact and future opportunities (by Sam Waes)Verhaert Masters in Innovation
 
Building an innovation culture, steering individual and team behavior (by Möb...
Building an innovation culture, steering individual and team behavior (by Möb...Building an innovation culture, steering individual and team behavior (by Möb...
Building an innovation culture, steering individual and team behavior (by Möb...Verhaert Masters in Innovation
 
Is the start-up way of working really different than the corporate one (by Fr...
Is the start-up way of working really different than the corporate one (by Fr...Is the start-up way of working really different than the corporate one (by Fr...
Is the start-up way of working really different than the corporate one (by Fr...Verhaert Masters in Innovation
 
Is the house of quality still a valid model to manage innovation (by Dany Rob...
Is the house of quality still a valid model to manage innovation (by Dany Rob...Is the house of quality still a valid model to manage innovation (by Dany Rob...
Is the house of quality still a valid model to manage innovation (by Dany Rob...Verhaert Masters in Innovation
 
How to shape your innovation ecosystem to create impact in your organization ...
How to shape your innovation ecosystem to create impact in your organization ...How to shape your innovation ecosystem to create impact in your organization ...
How to shape your innovation ecosystem to create impact in your organization ...Verhaert Masters in Innovation
 
The evolution of the bicycle industry 50 years after eddy merckx' victory (by...
The evolution of the bicycle industry 50 years after eddy merckx' victory (by...The evolution of the bicycle industry 50 years after eddy merckx' victory (by...
The evolution of the bicycle industry 50 years after eddy merckx' victory (by...Verhaert Masters in Innovation
 
The drivers of value creation, 50 years of research (by Dany Robberecht)
The drivers of value creation, 50 years of research (by Dany Robberecht)The drivers of value creation, 50 years of research (by Dany Robberecht)
The drivers of value creation, 50 years of research (by Dany Robberecht)Verhaert Masters in Innovation
 
Multi-sided business models in smart cities (IoT Convention 2019)
Multi-sided business models in smart cities (IoT Convention 2019)Multi-sided business models in smart cities (IoT Convention 2019)
Multi-sided business models in smart cities (IoT Convention 2019)Verhaert Masters in Innovation
 
Dany Robberecht - The benefits of cross industry innovation
Dany Robberecht - The benefits of cross industry innovationDany Robberecht - The benefits of cross industry innovation
Dany Robberecht - The benefits of cross industry innovationVerhaert Masters in Innovation
 
Space 4.0 and the Belgian start-up ecosystem by Omar Mohout
Space 4.0 and the Belgian start-up ecosystem by Omar MohoutSpace 4.0 and the Belgian start-up ecosystem by Omar Mohout
Space 4.0 and the Belgian start-up ecosystem by Omar MohoutVerhaert Masters in Innovation
 

More from Verhaert Masters in Innovation (20)

Technology watch - AI in chemical industry
Technology watch - AI in chemical industryTechnology watch - AI in chemical industry
Technology watch - AI in chemical industry
 
Software language over the last 50 years, what will be next (by Pieter Zulian...
Software language over the last 50 years, what will be next (by Pieter Zulian...Software language over the last 50 years, what will be next (by Pieter Zulian...
Software language over the last 50 years, what will be next (by Pieter Zulian...
 
Geospatial technologies, the evolution and impact on our daily life (by Nicol...
Geospatial technologies, the evolution and impact on our daily life (by Nicol...Geospatial technologies, the evolution and impact on our daily life (by Nicol...
Geospatial technologies, the evolution and impact on our daily life (by Nicol...
 
Advanced human interfaces, the underestimated enabler for innovation (by Bert...
Advanced human interfaces, the underestimated enabler for innovation (by Bert...Advanced human interfaces, the underestimated enabler for innovation (by Bert...
Advanced human interfaces, the underestimated enabler for innovation (by Bert...
 
The first humanoid robot, wabot 1 (by Robrecht Van Velthoven)
The first humanoid robot, wabot 1 (by Robrecht Van Velthoven)The first humanoid robot, wabot 1 (by Robrecht Van Velthoven)
The first humanoid robot, wabot 1 (by Robrecht Van Velthoven)
 
The government as launching customer, a great opportunity for companies (by R...
The government as launching customer, a great opportunity for companies (by R...The government as launching customer, a great opportunity for companies (by R...
The government as launching customer, a great opportunity for companies (by R...
 
Landing on the moon, the impact and future opportunities (by Sam Waes)
Landing on the moon, the impact and future opportunities (by Sam Waes)Landing on the moon, the impact and future opportunities (by Sam Waes)
Landing on the moon, the impact and future opportunities (by Sam Waes)
 
Building an innovation culture, steering individual and team behavior (by Möb...
Building an innovation culture, steering individual and team behavior (by Möb...Building an innovation culture, steering individual and team behavior (by Möb...
Building an innovation culture, steering individual and team behavior (by Möb...
 
The era of pretotyping has arrived (by Kevin Douven)
The era of pretotyping has arrived (by Kevin Douven)The era of pretotyping has arrived (by Kevin Douven)
The era of pretotyping has arrived (by Kevin Douven)
 
Is the start-up way of working really different than the corporate one (by Fr...
Is the start-up way of working really different than the corporate one (by Fr...Is the start-up way of working really different than the corporate one (by Fr...
Is the start-up way of working really different than the corporate one (by Fr...
 
Behind the waterfall methodology (by Jan Buytaert)
Behind the waterfall methodology (by Jan Buytaert)Behind the waterfall methodology (by Jan Buytaert)
Behind the waterfall methodology (by Jan Buytaert)
 
Is the house of quality still a valid model to manage innovation (by Dany Rob...
Is the house of quality still a valid model to manage innovation (by Dany Rob...Is the house of quality still a valid model to manage innovation (by Dany Rob...
Is the house of quality still a valid model to manage innovation (by Dany Rob...
 
How to shape your innovation ecosystem to create impact in your organization ...
How to shape your innovation ecosystem to create impact in your organization ...How to shape your innovation ecosystem to create impact in your organization ...
How to shape your innovation ecosystem to create impact in your organization ...
 
The evolution of the bicycle industry 50 years after eddy merckx' victory (by...
The evolution of the bicycle industry 50 years after eddy merckx' victory (by...The evolution of the bicycle industry 50 years after eddy merckx' victory (by...
The evolution of the bicycle industry 50 years after eddy merckx' victory (by...
 
The drivers of value creation, 50 years of research (by Dany Robberecht)
The drivers of value creation, 50 years of research (by Dany Robberecht)The drivers of value creation, 50 years of research (by Dany Robberecht)
The drivers of value creation, 50 years of research (by Dany Robberecht)
 
Multi-sided business models in smart cities (IoT Convention 2019)
Multi-sided business models in smart cities (IoT Convention 2019)Multi-sided business models in smart cities (IoT Convention 2019)
Multi-sided business models in smart cities (IoT Convention 2019)
 
Space for Artificial Intelligence
Space for Artificial IntelligenceSpace for Artificial Intelligence
Space for Artificial Intelligence
 
Dany Robberecht - The benefits of cross industry innovation
Dany Robberecht - The benefits of cross industry innovationDany Robberecht - The benefits of cross industry innovation
Dany Robberecht - The benefits of cross industry innovation
 
Space 4.0 and the Belgian start-up ecosystem by Omar Mohout
Space 4.0 and the Belgian start-up ecosystem by Omar MohoutSpace 4.0 and the Belgian start-up ecosystem by Omar Mohout
Space 4.0 and the Belgian start-up ecosystem by Omar Mohout
 
Going beyond horizons by Angelo Vermeulen
Going beyond horizons by Angelo VermeulenGoing beyond horizons by Angelo Vermeulen
Going beyond horizons by Angelo Vermeulen
 

Recently uploaded

Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Neo4j
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
Bluetooth Controlled Car with Arduino.pdf
Bluetooth Controlled Car with Arduino.pdfBluetooth Controlled Car with Arduino.pdf
Bluetooth Controlled Car with Arduino.pdfngoud9212
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraDeakin University
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsAndrey Dotsenko
 
Science&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdfScience&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdfjimielynbastida
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 

Recently uploaded (20)

Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024Build your next Gen AI Breakthrough - April 2024
Build your next Gen AI Breakthrough - April 2024
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptxE-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
E-Vehicle_Hacking_by_Parul Sharma_null_owasp.pptx
 
Bluetooth Controlled Car with Arduino.pdf
Bluetooth Controlled Car with Arduino.pdfBluetooth Controlled Car with Arduino.pdf
Bluetooth Controlled Car with Arduino.pdf
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
Hot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort Service
Hot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort ServiceHot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort Service
Hot Sexy call girls in Panjabi Bagh 🔝 9953056974 🔝 Delhi escort Service
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Artificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning eraArtificial intelligence in the post-deep learning era
Artificial intelligence in the post-deep learning era
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Science&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdfScience&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdf
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
The transition to renewables in India.pdf
The transition to renewables in India.pdfThe transition to renewables in India.pdf
The transition to renewables in India.pdf
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 

Integrating AI techniques to build meaningful product concepts (by Jochem Grietens)

  • 1. 1.1 Integrating AI techniques to build meaningful product concepts 1 CONFIDENTIAL Template Innovation Day 2018CONFIDENTIAL INTEGRATING AI TECHNIQUES TO BUILD MEANINGFUL PRODUCT CONCEPTS Jochem Grietens System engineer – A.I. passionate jochem.grietens@verhaert.com TRACK 1 - CIRCULAR ECONOMY FOR A BETTER WORLD
  • 2. 1.1 Integrating AI techniques to build meaningful product concepts 2 CONFIDENTIAL Introduction
  • 3. 1.1 Integrating AI techniques to build meaningful product concepts 3 CONFIDENTIAL 1. Introduction 2. A recycling use case: Hackathon 3. Machine learning: What does it mean to “see” ? 4. How does a machine “see” ? Content
  • 4. 1.1 Integrating AI techniques to build meaningful product concepts 4 CONFIDENTIAL “Fail fast, fail cheap, learn faster” Understanding comes from running through the cycle. Rapid prototyping credo
  • 5. 1.1 Integrating AI techniques to build meaningful product concepts 5 CONFIDENTIAL A recycling use case Load Hackathon Case
  • 6. 1.1 Integrating AI techniques to build meaningful product concepts 6 CONFIDENTIAL aaa Load hackathon 2018 • Theme A: Help The Community • Theme B: Change behavior • aim for a sustainable world • live a healthier life • become a better citizen
  • 7. 1.1 Integrating AI techniques to build meaningful product concepts 7 CONFIDENTIAL
  • 8. 1.1 Integrating AI techniques to build meaningful product concepts 8 CONFIDENTIAL 1. Business understanding Hackathon process
  • 9. 1.1 Integrating AI techniques to build meaningful product concepts 9 CONFIDENTIAL Closing the loop in a circular economy Challenges for companies: • Little incentive to close the loop • Companies have no control over the downstream process. Business understanding
  • 10. 1.1 Integrating AI techniques to build meaningful product concepts 10 CONFIDENTIAL Sorting is hard Sorting is boring Sorting is a community effort yellow for plastic and metal blue for paper green for glass Business understanding
  • 11. 1.1 Integrating AI techniques to build meaningful product concepts 11 CONFIDENTIAL Concept generation
  • 12. 1.1 Integrating AI techniques to build meaningful product concepts 12 CONFIDENTIAL 3. Data understanding 4. Data preparation 5. Modeling/app building Hackathon process
  • 13. 1.1 Integrating AI techniques to build meaningful product concepts 13 CONFIDENTIAL
  • 14. 1.1 Integrating AI techniques to build meaningful product concepts 14 CONFIDENTIAL Goals Help people sort Fun and engaging Create a community Help close the circular economy loop.
  • 15. 1.1 Integrating AI techniques to build meaningful product concepts 15 CONFIDENTIAL
  • 16. 1.1 Integrating AI techniques to build meaningful product concepts 16 CONFIDENTIAL
  • 17. 1.1 Integrating AI techniques to build meaningful product concepts 17 CONFIDENTIAL
  • 18. 1.1 Integrating AI techniques to build meaningful product concepts 18 CONFIDENTIAL
  • 19. 1.1 Integrating AI techniques to build meaningful product concepts 19 CONFIDENTIAL Hackathon process 6 Evaluation 7 Deployment
  • 20. 1.1 Integrating AI techniques to build meaningful product concepts 20 CONFIDENTIAL Architecture
  • 21. 1.1 Integrating AI techniques to build meaningful product concepts 21 CONFIDENTIAL Machine learning model What does it mean to “see”
  • 22. 1.1 Integrating AI techniques to build meaningful product concepts 22 CONFIDENTIAL What does it mean to “see” Primate visual system
  • 23. 1.1 Integrating AI techniques to build meaningful product concepts 23 CONFIDENTIAL What does it mean to “see”
  • 24. 1.1 Integrating AI techniques to build meaningful product concepts 24 CONFIDENTIAL “Seeing”: • Recognizing (=classification) • Localization • Segmentation • Understanding What does it mean to “see”
  • 25. 1.1 Integrating AI techniques to build meaningful product concepts 25 CONFIDENTIAL Neural network to fit our goal
  • 26. 1.1 Integrating AI techniques to build meaningful product concepts 26 CONFIDENTIAL How does a machine “see” ?
  • 27. 1.1 Integrating AI techniques to build meaningful product concepts 27 CONFIDENTIAL Neural network
  • 28. 1.1 Integrating AI techniques to build meaningful product concepts 28 CONFIDENTIAL Neural network yellow for plastic and metal blue for paper green for glass
  • 29. 1.1 Integrating AI techniques to build meaningful product concepts 29 CONFIDENTIAL 1. Input Encoding Neural network
  • 30. 1.1 Integrating AI techniques to build meaningful product concepts 30 CONFIDENTIAL Input Encoding Picture = 3 arrays of numbers Neural network R G B
  • 31. 1.1 Integrating AI techniques to build meaningful product concepts 31 CONFIDENTIAL Output encoding 1. metal  ( 1 0 0 ) 2. paper  ( 0 1 0 ) 3. Glass  ( 0 0 1 ) Neural network
  • 32. 1.1 Integrating AI techniques to build meaningful product concepts 32 CONFIDENTIAL Neural network ( 1 0 0 ) ( 0 1 0 ) ( 0 0 1 )
  • 33. 1.1 Integrating AI techniques to build meaningful product concepts 33 CONFIDENTIAL The neuron Neural network
  • 34. 1.1 Integrating AI techniques to build meaningful product concepts 34 CONFIDENTIAL Neural network
  • 35. 1.1 Integrating AI techniques to build meaningful product concepts 35 CONFIDENTIAL Neural network
  • 36. 1.1 Integrating AI techniques to build meaningful product concepts 36 CONFIDENTIAL Neural network
  • 37. 1.1 Integrating AI techniques to build meaningful product concepts 37 CONFIDENTIAL Convolutional neural network Conv. neural networkInput Output 0,9 0,1 0 yellow for plastic and metal blue for paper green for glass
  • 38. 1.1 Integrating AI techniques to build meaningful product concepts 38 CONFIDENTIAL Neural network training Forward pass
  • 39. 1.1 Integrating AI techniques to build meaningful product concepts 39 CONFIDENTIAL Neural network training 0,9 0,1 0 Prediction
  • 40. 1.1 Integrating AI techniques to build meaningful product concepts 40 CONFIDENTIAL Neural network training 0,9 0,1 0 Prediction 1 0 0 Truth COMPARE
  • 41. 1.1 Integrating AI techniques to build meaningful product concepts 41 CONFIDENTIAL Prediction Truth Calculate the error Neural network training 0,9 0,1 0 1 0 0
  • 42. 1.1 Integrating AI techniques to build meaningful product concepts 42 CONFIDENTIAL Neural network training Backwards pass Prediction Truth 0,9 0,1 0 1 0 0
  • 43. 1.1 Integrating AI techniques to build meaningful product concepts 43 CONFIDENTIAL Many layers stacked Deep neural network
  • 44. 1.1 Integrating AI techniques to build meaningful product concepts 44 CONFIDENTIAL Specific WIRING of the first regions for image recognition Deep convolutional neural network
  • 45. 1.1 Integrating AI techniques to build meaningful product concepts 45 CONFIDENTIAL • Convolution • Fully connected Convolutional neural network
  • 46. 1.1 Integrating AI techniques to build meaningful product concepts 46 CONFIDENTIAL Convolution = comparing to patterns Convolution
  • 47. 1.1 Integrating AI techniques to build meaningful product concepts 47 CONFIDENTIAL =6600 Convolution Feature learning Great match
  • 48. 1.1 Integrating AI techniques to build meaningful product concepts 48 CONFIDENTIAL = 0 Convolution Convolution Bad match
  • 49. 1.1 Integrating AI techniques to build meaningful product concepts 49 CONFIDENTIAL Feature maps
  • 50. 1.1 Integrating AI techniques to build meaningful product concepts 50 CONFIDENTIAL Neural network LEARNS the features from examples Convolutional neural network
  • 51. 1.1 Integrating AI techniques to build meaningful product concepts 51 CONFIDENTIAL Neural network LEARNS the features from examples Convolutional neural network
  • 52. 1.1 Integrating AI techniques to build meaningful product concepts 52 CONFIDENTIAL Convolutional network
  • 53. 1.1 Integrating AI techniques to build meaningful product concepts 53 CONFIDENTIAL Flattening
  • 54. 1.1 Integrating AI techniques to build meaningful product concepts 54 CONFIDENTIAL Flattening
  • 55. 1.1 Integrating AI techniques to build meaningful product concepts 55 CONFIDENTIAL Classification
  • 56. 1.1 Integrating AI techniques to build meaningful product concepts 56 CONFIDENTIAL Classification 0 1 Tesla Volkswagen One Hot encoding: 1 0 0 1 Tesla 0,2 0,8
  • 57. 1.1 Integrating AI techniques to build meaningful product concepts 57 CONFIDENTIAL Convolutional neural network
  • 58. 1.1 Integrating AI techniques to build meaningful product concepts 58 CONFIDENTIAL TrashNet dataset : to train on 2527 labeled images Way too little to learn a deep neural net “to see” AND “to recognize” Training data
  • 59. 1.1 Integrating AI techniques to build meaningful product concepts 59 CONFIDENTIAL Convolutional neural network Transfer learning = Learning to see on a different dataset.
  • 60. 1.1 Integrating AI techniques to build meaningful product concepts 60 CONFIDENTIAL Can we learn how to see on Cifar dataset: 60,000 32x32 color images in 10 different classes. Learn how to recognize on the trashnet database Transfer learning
  • 61. 1.1 Integrating AI techniques to build meaningful product concepts 61 CONFIDENTIAL Transfer learning Freeze Finetune
  • 62. 1.1 Integrating AI techniques to build meaningful product concepts 62 CONFIDENTIAL Learning by heart vs. learning general features Algorithm should have learned general features : • Visual effects of metallic light reflection • Can shape features • Size vs environment • … Instead it learned: Very specific features, like the shadow on the hand … Overtraining  MODEL DOES NOT GENERALIZE WELL
  • 63. 1.1 Integrating AI techniques to build meaningful product concepts 63 CONFIDENTIAL Central ML problem Performance on new data ? Test it! How to detect overfitting Training and tuning the models. Check performance during development. Don’t touch until the very end.
  • 64. 1.1 Integrating AI techniques to build meaningful product concepts 64 CONFIDENTIAL Detecting overfitting “Performance training set >> test set  likely overfitting.” Dealing with overfitting
  • 65. 1.1 Integrating AI techniques to build meaningful product concepts 65 CONFIDENTIAL More data - Data augmentation Dealing with overtraining
  • 66. 1.1 Integrating AI techniques to build meaningful product concepts 66 CONFIDENTIAL Dealing with overtraining X1 X2
  • 67. 1.1 Integrating AI techniques to build meaningful product concepts 67 CONFIDENTIAL Achieved • 70% accuracy on test set. • 65% in real world validation. Results
  • 68. 1.1 Integrating AI techniques to build meaningful product concepts 68 CONFIDENTIAL One group, five brands Our services are marketed through 5 brands each addressing specific missions in product development. INTEGRATED PRODUCT DEVELOPMENT ON-SITE PRODUCT DEVELOPMENT DIGITAL PRODUCTS DEVELOPMENT OPTICAL PRODUCTS DEVELOPMENT VENTURING