SlideShare uma empresa Scribd logo
1 de 24
Baixar para ler offline
A Simple AI Problem
That Wasn’t
Wei-Chao Chen 陳維超
Chief Digital Officer & SVP, Inventec Inc.
Co-Founder, Skywatch Inc.
chen.wei-chao@inventec.com
For ICPAI 2020, December 2020
2
Inventec Confidential
Smart Manufacturing
Digital twin of factories
Process Automation
o Automatic Optical
Inspection
o …
Predictive Analysis
o …
3
Inventec Confidential
Find Visual Defects on Laptops
How hard can it be?
Customer
Info
Logo
4
Inventec Confidential
Find Visual Defects on Laptops
How hard can it be?
Customer
Info
Logo
5
Inventec Confidential
o S1: Write a fancy diff program
Find Visual Defects on Laptops
How hard can it be?
Golden Defective
6
Inventec Confidential
o S1: Write a fancy diff program
o Variance between capture
Find Visual Defects on Laptops
How hard can it be?
7
Inventec Confidential
o S1: Write a fancy diff program
o Variance between capture
o S2: Use an object detector
Find Visual Defects on Laptops
How hard can it be?
8
Inventec Confidential
Inventec / Skywatch Laptop AOI Machine, v1.0, GTC 2019
9
Inventec Confidential
o S1: Write a fancy diff program
o Variance between capture
o S2: Use an object detector
o Lots of data to label
Find Visual Defects on Laptops
How hard can it be?
10
Inventec Confidential
o S1: Write a fancy diff program
o Variance between capture
o S2: Use an object detector
o Lots of data to label
o S3: Let us capture and label the data anyways
Find Visual Defects on Laptops
How hard can it be?
11
Inventec Confidential
o S1: Write a fancy diff program
o Variance between capture
o S2: Use an object detector
o Lots of data to label
o S3: Let us capture and label the data anyways
o You forgot to look at the sides
Find Visual Defects on Laptops
How hard can it be?
12
Inventec Confidential
o S1: Write a fancy diff program
o Variance between capture
o S2: Use an object detector
o Lots of data to label
o S3: Let us capture and label the data anyways
o You forgot to look at the sides
o S4: Build a proper machine
Find Visual Defects on Laptops
How hard can it be?
13
Inventec Confidential
S4: Build a proper machine
Surely it took a while and a bit of fortune
Inventec Laptop AOI Machine, v2.0, GTC 2020
14
Inventec Confidential
o S1: Write a fancy diff program
o Variance between capture
o S2: Use an object detector
o Lots of data to label
o S3: Let us capture and label the data anyways
o You forgot to look at the sides
o S4: Build a proper machine
o Well, but the product is obsolete before the model is ready
Find Visual Defects on Laptops
How hard can it be?
>6 Months!!
99+% yield, 1000s daily volume
15
Inventec Confidential
o S1: Write a fancy diff program
o Variance between capture
o S2: Use an object detector
o Lots of data to label
o S3: Let us capture and label the data anyways
o You forgot to look at the sides
o S4: Build a proper machine
o Well, but the product is obsolete before the model is ready
o S5: Use less labels with semi-supervised algorithm
Find Visual Defects on Laptops
How hard can it be?
16
Inventec Confidential
Semi-supervised defect detection
TrustMAE, WACV 2021
17
Inventec Confidential
o S1: Write a fancy diff program
o Variance between capture
o S2: Use an object detector
o Lots of data to label
o S3: Let us capture and label the data anyways
o You forgot to look at the sides
o S4: Build a proper machine
o Well, but the product is obsolete before the model is ready
o S5: Use less labels with semi-supervised algorithm
o Fine, but the accuracy is worse than expected
Find Visual Defects on Laptops
How hard can it be?
18
Inventec Confidential
o S1: Write a fancy diff program
o Variance between capture
o S2: Use an object detector
o Lots of data to label
o S3: Let us capture and label the data anyways
o You forgot to look at the sides
o S4: Build a proper machine
o Well, but the product is obsolete before the model is ready
o S5: Use less labels with semi-supervised algorithm
o Fine, but the accuracy is worse than expected
o S6: Wait, let us check if humans are better at it
o Well, turned out they are not
Find Visual Defects on Laptops
How hard can it be?
19
Inventec Confidential
o Passing criteria can vary across inspectors
The Weakest Link
To err is human
Visual
Criteria
20
Inventec Confidential
o Passing criteria can vary across inspectors
o Label quality, acceptance criteria hard to define
The Weakest Link
To err is human
Visual
Criteria
Time
Product
Type
21
Inventec Confidential
o S1: Write a fancy diff program
o Variance between capture
o S2: Use an object detector
o Lots of data to label
o S3: Let us capture and label the data anyways
o You forgot to look at the sides
o S4: Build a proper machine
o Well, but the product is obsolete before the model is ready
o S5: Use less labels with semi-supervised algorithm
o Fine, but the accuracy is worse than expected
o S6: Wait, let us check if humans are better at it
o Well, turned out they are not
o S7: Ok we beat the human, hurray!
Find Visual Defects on Laptops
How hard can it be?
22
Inventec Confidential
o S1: Write a fancy diff program
o Variance between capture
o S2: Use an object detector
o Lots of data to label
o S3: Let us capture and label the data anyways
o You forgot to look at the sides
o S4: Build a proper machine
o Well, but the product is obsolete before the model is ready
o S5: Use less labels with semi-supervised algorithm
o Fine, but the accuracy is worse than expected
o S6: Wait, let us check if humans are better at it
o Well, turned out they are not
o S7: Ok we beat the human, hurray!
o Your machine is too expensive
Find Visual Defects on Laptops
How hard can it be?
23
Inventec Confidential
o Talks
o “Edge AI Smart Manufacturing - Defect Detection and Beyond”, T.
Chen, W-C. Chen, in NVIDIA GTC 2019
o “Toward Taming the Training Data Complexity in Smart
Manufacturing”, D. Tan, H-H. Lee, Y-C. Chen, W-C. Chen, T. Chen,
in NVIDIA GTC 2020
o Papers
o “TrustMAE: A Noise-Resilient Defect Classification Framework
using Memory-Augmented Auto-Encoders with Trust Regions”, D.
Tan, Y-C. Chen, T. Chen, W-C. Chen, in WACV 2021
o “Demystifying Data and AI for Manufacturing: Case Studies from a
Major Computer Maker”, Y-C. Chen et al., in APSIPA Trans 2021.
References
Contact: chen.wei-chao@inventec.com
A Simple AI Problem
That Wasn’t
Wei-Chao Chen 陳維超
Chief Digital Officer & SVP, Inventec Inc.
Co-Founder, Skywatch Inc.
chen.wei-chao@inventec.com
For ICPAI 2020, December 2020

Mais conteúdo relacionado

Semelhante a A Simple AI Problem That Wasn’t: A Smart Manufacturing Case Study

Student Tech Portfolio 2
Student Tech  Portfolio 2Student Tech  Portfolio 2
Student Tech Portfolio 2Peter Helstrom
 
From Data Science to Production - deploy, scale, enjoy! / PyData Amsterdam - ...
From Data Science to Production - deploy, scale, enjoy! / PyData Amsterdam - ...From Data Science to Production - deploy, scale, enjoy! / PyData Amsterdam - ...
From Data Science to Production - deploy, scale, enjoy! / PyData Amsterdam - ...Sergii Khomenko
 
INTELLIGENT HELMET DETECTION USING OPENCV AND MACHINE LEARNING
INTELLIGENT HELMET DETECTION USING OPENCV AND MACHINE LEARNINGINTELLIGENT HELMET DETECTION USING OPENCV AND MACHINE LEARNING
INTELLIGENT HELMET DETECTION USING OPENCV AND MACHINE LEARNINGIRJET Journal
 
Virtual Reality Analytics
Virtual Reality AnalyticsVirtual Reality Analytics
Virtual Reality AnalyticsJoerg Osarek
 
Internet of Things & Open Hardware (LeanCamp Madrid 2012)
Internet of Things & Open Hardware (LeanCamp Madrid 2012)Internet of Things & Open Hardware (LeanCamp Madrid 2012)
Internet of Things & Open Hardware (LeanCamp Madrid 2012)iotmadrid
 
ASFWS 2013 - Cryptocat: récents défis en faisant la cryptographie plus facile...
ASFWS 2013 - Cryptocat: récents défis en faisant la cryptographie plus facile...ASFWS 2013 - Cryptocat: récents défis en faisant la cryptographie plus facile...
ASFWS 2013 - Cryptocat: récents défis en faisant la cryptographie plus facile...Cyber Security Alliance
 
Killing the golden calf of coding - We are Developers keynote
Killing the golden calf of coding - We are Developers keynoteKilling the golden calf of coding - We are Developers keynote
Killing the golden calf of coding - We are Developers keynoteChristian Heilmann
 
Dev Wars - iOS vs Android vs Titanium
Dev Wars - iOS vs Android vs TitaniumDev Wars - iOS vs Android vs Titanium
Dev Wars - iOS vs Android vs TitaniumVivochaLabs
 
Functional IoT: Introduction
Functional IoT: IntroductionFunctional IoT: Introduction
Functional IoT: IntroductionKiwamu Okabe
 
Faster Secure Software Development with Continuous Deployment - PH Days 2013
Faster Secure Software Development with Continuous Deployment - PH Days 2013Faster Secure Software Development with Continuous Deployment - PH Days 2013
Faster Secure Software Development with Continuous Deployment - PH Days 2013Nick Galbreath
 
Cybercrime and the developer 2021 style
Cybercrime and the developer 2021 styleCybercrime and the developer 2021 style
Cybercrime and the developer 2021 styleSteve Poole
 
iot hacking, smartlockpick
 iot hacking, smartlockpick iot hacking, smartlockpick
iot hacking, smartlockpickidsecconf
 
Needlesand haystacks i360-dublin
Needlesand haystacks i360-dublinNeedlesand haystacks i360-dublin
Needlesand haystacks i360-dublinDerek King
 
Week 11_Cchen Ching Heng
Week 11_Cchen Ching HengWeek 11_Cchen Ching Heng
Week 11_Cchen Ching Heng敬恆 陳
 
CppCat, an Ambitious C++ Code Analyzer from Tula
CppCat, an Ambitious C++ Code Analyzer from TulaCppCat, an Ambitious C++ Code Analyzer from Tula
CppCat, an Ambitious C++ Code Analyzer from TulaAndrey Karpov
 
Pc magazine may 2016
Pc magazine may 2016Pc magazine may 2016
Pc magazine may 2016Safrudin S
 
Hacking Soldering Robot with TERES-I DIY laptop
Hacking Soldering Robot with TERES-I DIY laptopHacking Soldering Robot with TERES-I DIY laptop
Hacking Soldering Robot with TERES-I DIY laptopOlimex Bulgaria
 
The 7 habits of data effective companies.pdf
The 7 habits of data effective companies.pdfThe 7 habits of data effective companies.pdf
The 7 habits of data effective companies.pdfLars Albertsson
 
The hardcore stuff i hack, experiences from past VAPT assignments
The hardcore stuff i hack, experiences from past VAPT assignmentsThe hardcore stuff i hack, experiences from past VAPT assignments
The hardcore stuff i hack, experiences from past VAPT assignmentsn|u - The Open Security Community
 

Semelhante a A Simple AI Problem That Wasn’t: A Smart Manufacturing Case Study (20)

Student Tech Portfolio 2
Student Tech  Portfolio 2Student Tech  Portfolio 2
Student Tech Portfolio 2
 
From Data Science to Production - deploy, scale, enjoy! / PyData Amsterdam - ...
From Data Science to Production - deploy, scale, enjoy! / PyData Amsterdam - ...From Data Science to Production - deploy, scale, enjoy! / PyData Amsterdam - ...
From Data Science to Production - deploy, scale, enjoy! / PyData Amsterdam - ...
 
INTELLIGENT HELMET DETECTION USING OPENCV AND MACHINE LEARNING
INTELLIGENT HELMET DETECTION USING OPENCV AND MACHINE LEARNINGINTELLIGENT HELMET DETECTION USING OPENCV AND MACHINE LEARNING
INTELLIGENT HELMET DETECTION USING OPENCV AND MACHINE LEARNING
 
Virtual Reality Analytics
Virtual Reality AnalyticsVirtual Reality Analytics
Virtual Reality Analytics
 
Internet of Things & Open Hardware (LeanCamp Madrid 2012)
Internet of Things & Open Hardware (LeanCamp Madrid 2012)Internet of Things & Open Hardware (LeanCamp Madrid 2012)
Internet of Things & Open Hardware (LeanCamp Madrid 2012)
 
ASFWS 2013 - Cryptocat: récents défis en faisant la cryptographie plus facile...
ASFWS 2013 - Cryptocat: récents défis en faisant la cryptographie plus facile...ASFWS 2013 - Cryptocat: récents défis en faisant la cryptographie plus facile...
ASFWS 2013 - Cryptocat: récents défis en faisant la cryptographie plus facile...
 
Killing the golden calf of coding - We are Developers keynote
Killing the golden calf of coding - We are Developers keynoteKilling the golden calf of coding - We are Developers keynote
Killing the golden calf of coding - We are Developers keynote
 
Dev Wars - iOS vs Android vs Titanium
Dev Wars - iOS vs Android vs TitaniumDev Wars - iOS vs Android vs Titanium
Dev Wars - iOS vs Android vs Titanium
 
Functional IoT: Introduction
Functional IoT: IntroductionFunctional IoT: Introduction
Functional IoT: Introduction
 
M.b.t.s. round 1 week 2 (2018)
M.b.t.s. round 1 week 2 (2018)M.b.t.s. round 1 week 2 (2018)
M.b.t.s. round 1 week 2 (2018)
 
Faster Secure Software Development with Continuous Deployment - PH Days 2013
Faster Secure Software Development with Continuous Deployment - PH Days 2013Faster Secure Software Development with Continuous Deployment - PH Days 2013
Faster Secure Software Development with Continuous Deployment - PH Days 2013
 
Cybercrime and the developer 2021 style
Cybercrime and the developer 2021 styleCybercrime and the developer 2021 style
Cybercrime and the developer 2021 style
 
iot hacking, smartlockpick
 iot hacking, smartlockpick iot hacking, smartlockpick
iot hacking, smartlockpick
 
Needlesand haystacks i360-dublin
Needlesand haystacks i360-dublinNeedlesand haystacks i360-dublin
Needlesand haystacks i360-dublin
 
Week 11_Cchen Ching Heng
Week 11_Cchen Ching HengWeek 11_Cchen Ching Heng
Week 11_Cchen Ching Heng
 
CppCat, an Ambitious C++ Code Analyzer from Tula
CppCat, an Ambitious C++ Code Analyzer from TulaCppCat, an Ambitious C++ Code Analyzer from Tula
CppCat, an Ambitious C++ Code Analyzer from Tula
 
Pc magazine may 2016
Pc magazine may 2016Pc magazine may 2016
Pc magazine may 2016
 
Hacking Soldering Robot with TERES-I DIY laptop
Hacking Soldering Robot with TERES-I DIY laptopHacking Soldering Robot with TERES-I DIY laptop
Hacking Soldering Robot with TERES-I DIY laptop
 
The 7 habits of data effective companies.pdf
The 7 habits of data effective companies.pdfThe 7 habits of data effective companies.pdf
The 7 habits of data effective companies.pdf
 
The hardcore stuff i hack, experiences from past VAPT assignments
The hardcore stuff i hack, experiences from past VAPT assignmentsThe hardcore stuff i hack, experiences from past VAPT assignments
The hardcore stuff i hack, experiences from past VAPT assignments
 

Último

04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessPixlogix Infotech
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountPuma Security, LLC
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 

Último (20)

04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Breaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path MountBreaking the Kubernetes Kill Chain: Host Path Mount
Breaking the Kubernetes Kill Chain: Host Path Mount
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 

A Simple AI Problem That Wasn’t: A Smart Manufacturing Case Study

  • 1. A Simple AI Problem That Wasn’t Wei-Chao Chen 陳維超 Chief Digital Officer & SVP, Inventec Inc. Co-Founder, Skywatch Inc. chen.wei-chao@inventec.com For ICPAI 2020, December 2020
  • 2. 2 Inventec Confidential Smart Manufacturing Digital twin of factories Process Automation o Automatic Optical Inspection o … Predictive Analysis o …
  • 3. 3 Inventec Confidential Find Visual Defects on Laptops How hard can it be? Customer Info Logo
  • 4. 4 Inventec Confidential Find Visual Defects on Laptops How hard can it be? Customer Info Logo
  • 5. 5 Inventec Confidential o S1: Write a fancy diff program Find Visual Defects on Laptops How hard can it be? Golden Defective
  • 6. 6 Inventec Confidential o S1: Write a fancy diff program o Variance between capture Find Visual Defects on Laptops How hard can it be?
  • 7. 7 Inventec Confidential o S1: Write a fancy diff program o Variance between capture o S2: Use an object detector Find Visual Defects on Laptops How hard can it be?
  • 8. 8 Inventec Confidential Inventec / Skywatch Laptop AOI Machine, v1.0, GTC 2019
  • 9. 9 Inventec Confidential o S1: Write a fancy diff program o Variance between capture o S2: Use an object detector o Lots of data to label Find Visual Defects on Laptops How hard can it be?
  • 10. 10 Inventec Confidential o S1: Write a fancy diff program o Variance between capture o S2: Use an object detector o Lots of data to label o S3: Let us capture and label the data anyways Find Visual Defects on Laptops How hard can it be?
  • 11. 11 Inventec Confidential o S1: Write a fancy diff program o Variance between capture o S2: Use an object detector o Lots of data to label o S3: Let us capture and label the data anyways o You forgot to look at the sides Find Visual Defects on Laptops How hard can it be?
  • 12. 12 Inventec Confidential o S1: Write a fancy diff program o Variance between capture o S2: Use an object detector o Lots of data to label o S3: Let us capture and label the data anyways o You forgot to look at the sides o S4: Build a proper machine Find Visual Defects on Laptops How hard can it be?
  • 13. 13 Inventec Confidential S4: Build a proper machine Surely it took a while and a bit of fortune Inventec Laptop AOI Machine, v2.0, GTC 2020
  • 14. 14 Inventec Confidential o S1: Write a fancy diff program o Variance between capture o S2: Use an object detector o Lots of data to label o S3: Let us capture and label the data anyways o You forgot to look at the sides o S4: Build a proper machine o Well, but the product is obsolete before the model is ready Find Visual Defects on Laptops How hard can it be? >6 Months!! 99+% yield, 1000s daily volume
  • 15. 15 Inventec Confidential o S1: Write a fancy diff program o Variance between capture o S2: Use an object detector o Lots of data to label o S3: Let us capture and label the data anyways o You forgot to look at the sides o S4: Build a proper machine o Well, but the product is obsolete before the model is ready o S5: Use less labels with semi-supervised algorithm Find Visual Defects on Laptops How hard can it be?
  • 16. 16 Inventec Confidential Semi-supervised defect detection TrustMAE, WACV 2021
  • 17. 17 Inventec Confidential o S1: Write a fancy diff program o Variance between capture o S2: Use an object detector o Lots of data to label o S3: Let us capture and label the data anyways o You forgot to look at the sides o S4: Build a proper machine o Well, but the product is obsolete before the model is ready o S5: Use less labels with semi-supervised algorithm o Fine, but the accuracy is worse than expected Find Visual Defects on Laptops How hard can it be?
  • 18. 18 Inventec Confidential o S1: Write a fancy diff program o Variance between capture o S2: Use an object detector o Lots of data to label o S3: Let us capture and label the data anyways o You forgot to look at the sides o S4: Build a proper machine o Well, but the product is obsolete before the model is ready o S5: Use less labels with semi-supervised algorithm o Fine, but the accuracy is worse than expected o S6: Wait, let us check if humans are better at it o Well, turned out they are not Find Visual Defects on Laptops How hard can it be?
  • 19. 19 Inventec Confidential o Passing criteria can vary across inspectors The Weakest Link To err is human Visual Criteria
  • 20. 20 Inventec Confidential o Passing criteria can vary across inspectors o Label quality, acceptance criteria hard to define The Weakest Link To err is human Visual Criteria Time Product Type
  • 21. 21 Inventec Confidential o S1: Write a fancy diff program o Variance between capture o S2: Use an object detector o Lots of data to label o S3: Let us capture and label the data anyways o You forgot to look at the sides o S4: Build a proper machine o Well, but the product is obsolete before the model is ready o S5: Use less labels with semi-supervised algorithm o Fine, but the accuracy is worse than expected o S6: Wait, let us check if humans are better at it o Well, turned out they are not o S7: Ok we beat the human, hurray! Find Visual Defects on Laptops How hard can it be?
  • 22. 22 Inventec Confidential o S1: Write a fancy diff program o Variance between capture o S2: Use an object detector o Lots of data to label o S3: Let us capture and label the data anyways o You forgot to look at the sides o S4: Build a proper machine o Well, but the product is obsolete before the model is ready o S5: Use less labels with semi-supervised algorithm o Fine, but the accuracy is worse than expected o S6: Wait, let us check if humans are better at it o Well, turned out they are not o S7: Ok we beat the human, hurray! o Your machine is too expensive Find Visual Defects on Laptops How hard can it be?
  • 23. 23 Inventec Confidential o Talks o “Edge AI Smart Manufacturing - Defect Detection and Beyond”, T. Chen, W-C. Chen, in NVIDIA GTC 2019 o “Toward Taming the Training Data Complexity in Smart Manufacturing”, D. Tan, H-H. Lee, Y-C. Chen, W-C. Chen, T. Chen, in NVIDIA GTC 2020 o Papers o “TrustMAE: A Noise-Resilient Defect Classification Framework using Memory-Augmented Auto-Encoders with Trust Regions”, D. Tan, Y-C. Chen, T. Chen, W-C. Chen, in WACV 2021 o “Demystifying Data and AI for Manufacturing: Case Studies from a Major Computer Maker”, Y-C. Chen et al., in APSIPA Trans 2021. References Contact: chen.wei-chao@inventec.com
  • 24. A Simple AI Problem That Wasn’t Wei-Chao Chen 陳維超 Chief Digital Officer & SVP, Inventec Inc. Co-Founder, Skywatch Inc. chen.wei-chao@inventec.com For ICPAI 2020, December 2020