Submit Search
Upload
Using ml to accelerate failure analysis
•
Download as PPTX, PDF
•
0 likes
•
118 views
Heemeng Foo
Follow
This is a talk I gave on 2 Sept 2020 as part of Sofy.ai's webinar series.
Read less
Read more
Engineering
Report
Share
Report
Share
1 of 14
Download now
Recommended
Why code?
Why code?
János Divényi
Resume
Resume
Joseph Falcone
Free PMP Sample Q & A
Free PMP Sample Q & A
OSP International LLC
Software Engineering Manager
Software Engineering Manager
Shaun Nicholls
Evaluating Collaboration Tools for Your Small Business
Evaluating Collaboration Tools for Your Small Business
Samepage
Improving software quality for the future of connected vehicles
Improving software quality for the future of connected vehicles
Devon Bleibtrey
Stefan Geissler kairntech - SDC Nice Apr 2019
Stefan Geissler kairntech - SDC Nice Apr 2019
Stefan Geißler
Running a small, high tech consulting firm - lessons learned
Running a small, high tech consulting firm - lessons learned
Pere Ferrera Bertran
Recommended
Why code?
Why code?
János Divényi
Resume
Resume
Joseph Falcone
Free PMP Sample Q & A
Free PMP Sample Q & A
OSP International LLC
Software Engineering Manager
Software Engineering Manager
Shaun Nicholls
Evaluating Collaboration Tools for Your Small Business
Evaluating Collaboration Tools for Your Small Business
Samepage
Improving software quality for the future of connected vehicles
Improving software quality for the future of connected vehicles
Devon Bleibtrey
Stefan Geissler kairntech - SDC Nice Apr 2019
Stefan Geissler kairntech - SDC Nice Apr 2019
Stefan Geißler
Running a small, high tech consulting firm - lessons learned
Running a small, high tech consulting firm - lessons learned
Pere Ferrera Bertran
SIM RTP Meeting - So Who's Using Open Source Anyway?
SIM RTP Meeting - So Who's Using Open Source Anyway?
Alex Meadows
MVP (Minimum Viable Product) Readiness | Boost Labs
MVP (Minimum Viable Product) Readiness | Boost Labs
Boost Labs
Google Apps for Work
Google Apps for Work
Physicians Agent™ Network
IC-SDV 2019: Down-to-earth machine learning: What you always wanted your data...
IC-SDV 2019: Down-to-earth machine learning: What you always wanted your data...
Dr. Haxel Consult
The Latest Advances in Generative AI_ Exploring New Technology for Data Integ...
The Latest Advances in Generative AI_ Exploring New Technology for Data Integ...
Safe Software
Top Python development Companies to outsource
Top Python development Companies to outsource
Mindfire LLC
2019 12 Clojure/conj: Love Letter To Clojure, and A Datomic Experience Report
2019 12 Clojure/conj: Love Letter To Clojure, and A Datomic Experience Report
Gene Kim
What's Next: Ogilvy x Google Chatbots Partnership
What's Next: Ogilvy x Google Chatbots Partnership
Ogilvy Consulting
What are the Best Practices for Enterprise Software Applications?
What are the Best Practices for Enterprise Software Applications?
BoTree Technologies
Experteer for ICMA: Applied Machine Learning. Smart Process Automation with AI
Experteer for ICMA: Applied Machine Learning. Smart Process Automation with AI
Alexander Chukovski
Demystifying ML/AI
Demystifying ML/AI
Matthew Reynolds
The Power of < Artificial Intelligence >
The Power of < Artificial Intelligence >
Merelda
An introduction to AI in Test Engineering
An introduction to AI in Test Engineering
Heemeng Foo
How to drive more value from Innovation Initiatives
How to drive more value from Innovation Initiatives
VMware Tanzu
Maintenance Technical Debt
Maintenance Technical Debt
Globant
AI hype or reality
AI hype or reality
Awantik Das
Hewlett-Packard Enterprises (HPE)
Hewlett-Packard Enterprises (HPE)
Levi Saada
MLOps - Getting Machine Learning Into Production
MLOps - Getting Machine Learning Into Production
Michael Pearce
2024-02-24_Session 1 - PMLE_UPDATED.pptx
2024-02-24_Session 1 - PMLE_UPDATED.pptx
gdgsurrey
4 - Overview of Generative AI Session#4.pptx
4 - Overview of Generative AI Session#4.pptx
Sumathy
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
KOUSTAV SARKAR
Hostel management system project report..pdf
Hostel management system project report..pdf
Kamal Acharya
More Related Content
Similar to Using ml to accelerate failure analysis
SIM RTP Meeting - So Who's Using Open Source Anyway?
SIM RTP Meeting - So Who's Using Open Source Anyway?
Alex Meadows
MVP (Minimum Viable Product) Readiness | Boost Labs
MVP (Minimum Viable Product) Readiness | Boost Labs
Boost Labs
Google Apps for Work
Google Apps for Work
Physicians Agent™ Network
IC-SDV 2019: Down-to-earth machine learning: What you always wanted your data...
IC-SDV 2019: Down-to-earth machine learning: What you always wanted your data...
Dr. Haxel Consult
The Latest Advances in Generative AI_ Exploring New Technology for Data Integ...
The Latest Advances in Generative AI_ Exploring New Technology for Data Integ...
Safe Software
Top Python development Companies to outsource
Top Python development Companies to outsource
Mindfire LLC
2019 12 Clojure/conj: Love Letter To Clojure, and A Datomic Experience Report
2019 12 Clojure/conj: Love Letter To Clojure, and A Datomic Experience Report
Gene Kim
What's Next: Ogilvy x Google Chatbots Partnership
What's Next: Ogilvy x Google Chatbots Partnership
Ogilvy Consulting
What are the Best Practices for Enterprise Software Applications?
What are the Best Practices for Enterprise Software Applications?
BoTree Technologies
Experteer for ICMA: Applied Machine Learning. Smart Process Automation with AI
Experteer for ICMA: Applied Machine Learning. Smart Process Automation with AI
Alexander Chukovski
Demystifying ML/AI
Demystifying ML/AI
Matthew Reynolds
The Power of < Artificial Intelligence >
The Power of < Artificial Intelligence >
Merelda
An introduction to AI in Test Engineering
An introduction to AI in Test Engineering
Heemeng Foo
How to drive more value from Innovation Initiatives
How to drive more value from Innovation Initiatives
VMware Tanzu
Maintenance Technical Debt
Maintenance Technical Debt
Globant
AI hype or reality
AI hype or reality
Awantik Das
Hewlett-Packard Enterprises (HPE)
Hewlett-Packard Enterprises (HPE)
Levi Saada
MLOps - Getting Machine Learning Into Production
MLOps - Getting Machine Learning Into Production
Michael Pearce
2024-02-24_Session 1 - PMLE_UPDATED.pptx
2024-02-24_Session 1 - PMLE_UPDATED.pptx
gdgsurrey
4 - Overview of Generative AI Session#4.pptx
4 - Overview of Generative AI Session#4.pptx
Sumathy
Similar to Using ml to accelerate failure analysis
(20)
SIM RTP Meeting - So Who's Using Open Source Anyway?
SIM RTP Meeting - So Who's Using Open Source Anyway?
MVP (Minimum Viable Product) Readiness | Boost Labs
MVP (Minimum Viable Product) Readiness | Boost Labs
Google Apps for Work
Google Apps for Work
IC-SDV 2019: Down-to-earth machine learning: What you always wanted your data...
IC-SDV 2019: Down-to-earth machine learning: What you always wanted your data...
The Latest Advances in Generative AI_ Exploring New Technology for Data Integ...
The Latest Advances in Generative AI_ Exploring New Technology for Data Integ...
Top Python development Companies to outsource
Top Python development Companies to outsource
2019 12 Clojure/conj: Love Letter To Clojure, and A Datomic Experience Report
2019 12 Clojure/conj: Love Letter To Clojure, and A Datomic Experience Report
What's Next: Ogilvy x Google Chatbots Partnership
What's Next: Ogilvy x Google Chatbots Partnership
What are the Best Practices for Enterprise Software Applications?
What are the Best Practices for Enterprise Software Applications?
Experteer for ICMA: Applied Machine Learning. Smart Process Automation with AI
Experteer for ICMA: Applied Machine Learning. Smart Process Automation with AI
Demystifying ML/AI
Demystifying ML/AI
The Power of < Artificial Intelligence >
The Power of < Artificial Intelligence >
An introduction to AI in Test Engineering
An introduction to AI in Test Engineering
How to drive more value from Innovation Initiatives
How to drive more value from Innovation Initiatives
Maintenance Technical Debt
Maintenance Technical Debt
AI hype or reality
AI hype or reality
Hewlett-Packard Enterprises (HPE)
Hewlett-Packard Enterprises (HPE)
MLOps - Getting Machine Learning Into Production
MLOps - Getting Machine Learning Into Production
2024-02-24_Session 1 - PMLE_UPDATED.pptx
2024-02-24_Session 1 - PMLE_UPDATED.pptx
4 - Overview of Generative AI Session#4.pptx
4 - Overview of Generative AI Session#4.pptx
Recently uploaded
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
KOUSTAV SARKAR
Hostel management system project report..pdf
Hostel management system project report..pdf
Kamal Acharya
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
Arindam Chakraborty, Ph.D., P.E. (CA, TX)
data_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdf
JiananWang21
Thermal Engineering -unit - III & IV.ppt
Thermal Engineering -unit - III & IV.ppt
DineshKumar4165
Computer Networks Basics of Network Devices
Computer Networks Basics of Network Devices
ChandrakantDivate1
Design For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the start
Quintin Balsdon
Online food ordering system project report.pdf
Online food ordering system project report.pdf
Kamal Acharya
A Study of Urban Area Plan for Pabna Municipality
A Study of Urban Area Plan for Pabna Municipality
Morshed Ahmed Rahath
Online electricity billing project report..pdf
Online electricity billing project report..pdf
Kamal Acharya
Thermal Engineering Unit - I & II . ppt
Thermal Engineering Unit - I & II . ppt
DineshKumar4165
AIRCANVAS[1].pdf mini project for btech students
AIRCANVAS[1].pdf mini project for btech students
vanyagupta248
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
drmkjayanthikannan
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Arindam Chakraborty, Ph.D., P.E. (CA, TX)
PE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and properties
sarkmank1
Verification of thevenin's theorem for BEEE Lab (1).pptx
Verification of thevenin's theorem for BEEE Lab (1).pptx
chumtiyababu
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Kandungan 087776558899
Integrated Test Rig For HTFE-25 - Neometrix
Integrated Test Rig For HTFE-25 - Neometrix
Neometrix_Engineering_Pvt_Ltd
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
AldoGarca30
Wadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptx
NadaHaitham1
Recently uploaded
(20)
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
HAND TOOLS USED AT ELECTRONICS WORK PRESENTED BY KOUSTAV SARKAR
Hostel management system project report..pdf
Hostel management system project report..pdf
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
data_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdf
Thermal Engineering -unit - III & IV.ppt
Thermal Engineering -unit - III & IV.ppt
Computer Networks Basics of Network Devices
Computer Networks Basics of Network Devices
Design For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the start
Online food ordering system project report.pdf
Online food ordering system project report.pdf
A Study of Urban Area Plan for Pabna Municipality
A Study of Urban Area Plan for Pabna Municipality
Online electricity billing project report..pdf
Online electricity billing project report..pdf
Thermal Engineering Unit - I & II . ppt
Thermal Engineering Unit - I & II . ppt
AIRCANVAS[1].pdf mini project for btech students
AIRCANVAS[1].pdf mini project for btech students
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
PE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and properties
Verification of thevenin's theorem for BEEE Lab (1).pptx
Verification of thevenin's theorem for BEEE Lab (1).pptx
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Cara Menggugurkan Sperma Yang Masuk Rahim Biyar Tidak Hamil
Integrated Test Rig For HTFE-25 - Neometrix
Integrated Test Rig For HTFE-25 - Neometrix
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
Wadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptx
Using ml to accelerate failure analysis
1.
© Hee-Meng Foo
2020
2.
© Hee-Meng Foo
2020 A little about me ● Worked on Genetic Algorithms and optimization problems in grad school ● Did a course in Neural Networks there too ● Been building/leading Quality/Test engineering teams for about 14 years ● Yahoo for 6+6 yrs, Climate Corp 2.5 yrs ● Started looking into Data Science, Machine Learning and Deep Learning again in 2015 on the side If you’d like to connect, just search for “Heemeng” on Linkedin and look for this
3.
© Hee-Meng Foo
2020 What Is Quality?
4.
© Hee-Meng Foo
2020 Quality is in the eye of the beholder
5.
© Hee-Meng Foo
2020 Quality is about user perception “Quality means providing value to the customer; that is, offering conditions of product use or service that meet or exceed customer’s expectations, yet are still affordable. Quality also takes into account the reduction of waste that a product may cause to the environment or human society, yet still allowing the manufacturing company to maintain customer satisfaction.” Enrique Diaz, Geneva Business News, Aug 2014 In “Software Quality: The Top 10 Metrics to Build Confidence”, John Lafleur listed down “Defect removal efficiency” as one of the metrics
6.
© Hee-Meng Foo
2020 The Stages of MTTR Mean Time to Resolution (MTTR) MTT Detection MTT Know MTT Fix MTT Verify Triage Isolate Diagnose
7.
© Hee-Meng Foo
2020 The Stages of MTTR Mean Time to Resolution (MTTR) MTT Detection MTT Know MTT Fix MTT Verify Triage Isolate Diagnose
8.
© Hee-Meng Foo
2020 Why Bug Triage? ● Takes up a lot of time (at least 30mins every day) ● Takes up expensive resource ○ Test/QA manager’s time ○ Engineering manager’s time ○ Lead engineer’s time ○ Product manager’s time ● What usually happens is that not urgent bugs pile up (dirty dishes analogy)
9.
© Hee-Meng Foo
2020 What this talk is about ● An exploration into the use of ML techniques to perform bug triage ○ Getting the data ○ Data exploration ○ Using traditional ML techniques ○ Using Tensorflow 2.0 ○ Using BlazingText from AWS Sagemaker (very briefly) ○ Using Google’s AutoML (Natural Language) (very briefly) Key assumption: you understand the basics of Machine Learning esp Classification
10.
© Hee-Meng Foo
2020 A General Recipe ● Obtaining and processing training data ● Formatting the data into the form needed for training ● Understanding the data ● Try out various ML algorithms to understand how they perform ○ Small data sets - traditional ML algorithms ○ Large data sets - Deep Neural Networks ● Hyperparameter tuning ● Package up and deploy
11.
© Hee-Meng Foo
2020 Material for this talk ● GitLab repo - https://gitlab.com/foohm71/octopus2 ● Medium Articles: ○ Building a deployable Jira Bug Classification Engine in Tensorflow ○ Building a deployable Jira Bug Classification Engine using Amazon Sagemaker ○ Building a deployable Jira Bug Classification Engine using Google AutoML
12.
© Hee-Meng Foo
2020 Deep Dive
13.
© Hee-Meng Foo
2020 Some Key Takeaways ● Getting and cleaning data can be challenging ● Getting a good ML or DNN algorithm takes some work ● A basic deployable ML engine is not difficult to create ○ Getting it to production grade is not so simple - DevOps skills needed ● Cloud services are making building ML engines easier and easier ● At the end of the day, you need to understand your data
14.
© Hee-Meng Foo
2020 Q&A
Download now