SlideShare a Scribd company logo
1 of 17
@vinaya1980 @hrishikarekar
TESTING IN THE AGE OF MACHINE LEARNING
March 2016
https://www.youtube.com/watch?v=DCgHsxISE0Q
W H E R E A R E
W E H E A D E D
httpsweforum.org/agenda/2017/01/worried-
about-ai-taking-your-job-its-already-happening-in-
japan?utm_content=buffera14af&utm_medium=s
ocial&utm_source=twitter.com&utm_campaign=b
uffer
THE WORLD OF ARTIFICIAL INTELLIGENCE
NLP
Neural Networks
MACHINE LEARNING
DEEP LEARNING
…..
THE FUTURE IS ALREADY HERE
Google RankBrain
Assistants
HOW DOES IT WORK
Supervised
• Labelled data
• Given new
data, predict
outcome
• Classification
Unsupervised
• No labels
• Find hidden
structures
• Clustering
Reinforcement
• Decision
process
• Actions are
rewarded or
punished
• Learns to
optimize
rewards
http://scikit-learn.org/
LEARNING FROM DATA
SUPERVISED LEARNING - CLASSIFCATION
http://www.mikedeff.in/MLIntro.PNG
INTO THE REALM OF PROBABILITIES
Y = f ( x ) Y ≈ f ( x )
What is scrum ?
{
"Prediction": {
"details": {
"Algorithm": "SGD",
"PredictiveModelType": "MULTICLASS"
},
"predictedLabel": "definition",
"predictedScores": {
"advantages": 0.0001860455668065697,
"characteristics": 0.00006915141420904547,
"compare": 0.00017757616296876222,
"definition": 0.9970965385437012,
"disadvantages": 0.0000534967657586094,
}
}
}
Can you tell me about scrum ?
{
"Prediction": {
"details": {
"Algorithm": "SGD",
"PredictiveModelType": "MULTICLASS"
},
"predictedLabel": "definition",
"predictedScores": {
"advantages": 0.01977257989346981,
"characteristics": 0.022757112979888916,
"compare": 0.008386141620576382,
"definition": 0.21092116832733154,
"disadvantages": 0.04002799838781357
}
}
}
TOLERANCE LEVELS
Y ≈ f ( x )
Know the probability that is within acceptable limits
EVALUATE WITH DIFFERENT MODELS
Evaluate against a set of
algorithms to iterate towards a
model that’s closest
representation and for further
tuning
https://s3.amazonaws.com/MLMastery/MachineLearningAlgorithms.png?__s=h4reg8jqwyg4sz3bzdqf
EVALUATION – DATA SET APPROACHES
Random split
• 70% train, 30% test
K-fold cross validation
Split into 3 datasets
• #1 Train on 1 and 2, test on 3
• #2 Train on 2 and 3, test on 1
• #3 Train on 1 and 3, test on 2
Never use the same dataset for training and evaluating
ITERATIVE – LEARNING PROCESS
Be prepared to throw the model and start again 
MODEL ACCURACY - CONFUSION MATRIX
Strive for better models, not 100% accurate.
OVERFITTING
MODEL IS AS GOOD AS THE TRAINING DATA
If all of the algorithms perform poorly,
• it maybe worth considering if there is a lack of learning
structure in the data set
• some transformation needed to make the structure more
learnable
• remove unnecessary noise - stop words are typically
removed because they cause unnecessary noise)
SUMMARY
Machine Learning applications demand a shift in testing
approach
• Use objective acceptance levels to evaluate the application
• Express test outcomes in statistical terms
• Have a high level understanding of the underlying working of
the application
@vinaya1980 @hrishikarekar
THANK YOU

More Related Content

What's hot

What is Regression Testing? | Edureka
What is Regression Testing? | EdurekaWhat is Regression Testing? | Edureka
What is Regression Testing? | EdurekaEdureka!
 
Testing Metrics - Making your tests visible
Testing Metrics - Making your tests visibleTesting Metrics - Making your tests visible
Testing Metrics - Making your tests visibleAlper Mermer
 
4.4.2013 Software Quality - Regression Testing Automated and Manual - RFT/RQM
4.4.2013 Software Quality - Regression Testing Automated and Manual - RFT/RQM4.4.2013 Software Quality - Regression Testing Automated and Manual - RFT/RQM
4.4.2013 Software Quality - Regression Testing Automated and Manual - RFT/RQMIBM Rational
 
How QA engineers could affect quality?
How QA engineers could affect quality?How QA engineers could affect quality?
How QA engineers could affect quality?Mikalai Alimenkou
 
Pitfalls of Test Automation
Pitfalls of Test AutomationPitfalls of Test Automation
Pitfalls of Test AutomationReload! A/S
 
Top 5 pitfalls of software test automatiion
Top 5 pitfalls of software test automatiionTop 5 pitfalls of software test automatiion
Top 5 pitfalls of software test automatiionekatechserv
 
Automated visual-regression-testing (1)
Automated visual-regression-testing (1)Automated visual-regression-testing (1)
Automated visual-regression-testing (1)Sriram Angajala
 
End-to-End Test Automation for Both Horizontal and Vertical Scale
End-to-End Test Automation for Both Horizontal and Vertical ScaleEnd-to-End Test Automation for Both Horizontal and Vertical Scale
End-to-End Test Automation for Both Horizontal and Vertical ScaleErdem YILDIRIM
 
Understand regression testing
Understand regression testingUnderstand regression testing
Understand regression testinggaoliang641
 
It Seemed a Good Idea at the Time: Intelligent Mistakes in Test Automation
It Seemed a Good Idea at the Time: Intelligent Mistakes in Test AutomationIt Seemed a Good Idea at the Time: Intelligent Mistakes in Test Automation
It Seemed a Good Idea at the Time: Intelligent Mistakes in Test AutomationTechWell
 
Solano Labs presented at MassTLC's automated testing
Solano Labs presented at MassTLC's automated testingSolano Labs presented at MassTLC's automated testing
Solano Labs presented at MassTLC's automated testingMassTLC
 
Defect root cause analysis, Андрей Титаренко
Defect root cause analysis, Андрей ТитаренкоDefect root cause analysis, Андрей Титаренко
Defect root cause analysis, Андрей ТитаренкоSigma Software
 
End to end testing - strategies
End to end testing - strategiesEnd to end testing - strategies
End to end testing - strategiesanuvip
 
Presentation1
Presentation1Presentation1
Presentation1anuvip
 
Management Issues in Test Automation
Management Issues in Test AutomationManagement Issues in Test Automation
Management Issues in Test AutomationTechWell
 
ISTQB Advanced Test Manager Training
ISTQB Advanced Test Manager TrainingISTQB Advanced Test Manager Training
ISTQB Advanced Test Manager TrainingHiraQureshi22
 
How Automation is Changing The Testing Scene
How Automation is Changing The Testing SceneHow Automation is Changing The Testing Scene
How Automation is Changing The Testing Scenesuneratechnologies
 
Crawl Walk and Run to Continuous Delivery
Crawl Walk and Run to Continuous DeliveryCrawl Walk and Run to Continuous Delivery
Crawl Walk and Run to Continuous DeliveryDavid Batten
 

What's hot (20)

What is Regression Testing? | Edureka
What is Regression Testing? | EdurekaWhat is Regression Testing? | Edureka
What is Regression Testing? | Edureka
 
Testing Metrics - Making your tests visible
Testing Metrics - Making your tests visibleTesting Metrics - Making your tests visible
Testing Metrics - Making your tests visible
 
4.4.2013 Software Quality - Regression Testing Automated and Manual - RFT/RQM
4.4.2013 Software Quality - Regression Testing Automated and Manual - RFT/RQM4.4.2013 Software Quality - Regression Testing Automated and Manual - RFT/RQM
4.4.2013 Software Quality - Regression Testing Automated and Manual - RFT/RQM
 
How QA engineers could affect quality?
How QA engineers could affect quality?How QA engineers could affect quality?
How QA engineers could affect quality?
 
Pitfalls of Test Automation
Pitfalls of Test AutomationPitfalls of Test Automation
Pitfalls of Test Automation
 
Top 5 pitfalls of software test automatiion
Top 5 pitfalls of software test automatiionTop 5 pitfalls of software test automatiion
Top 5 pitfalls of software test automatiion
 
Automated visual-regression-testing (1)
Automated visual-regression-testing (1)Automated visual-regression-testing (1)
Automated visual-regression-testing (1)
 
End-to-End Test Automation for Both Horizontal and Vertical Scale
End-to-End Test Automation for Both Horizontal and Vertical ScaleEnd-to-End Test Automation for Both Horizontal and Vertical Scale
End-to-End Test Automation for Both Horizontal and Vertical Scale
 
Understand regression testing
Understand regression testingUnderstand regression testing
Understand regression testing
 
It Seemed a Good Idea at the Time: Intelligent Mistakes in Test Automation
It Seemed a Good Idea at the Time: Intelligent Mistakes in Test AutomationIt Seemed a Good Idea at the Time: Intelligent Mistakes in Test Automation
It Seemed a Good Idea at the Time: Intelligent Mistakes in Test Automation
 
Solano Labs presented at MassTLC's automated testing
Solano Labs presented at MassTLC's automated testingSolano Labs presented at MassTLC's automated testing
Solano Labs presented at MassTLC's automated testing
 
Defect root cause analysis, Андрей Титаренко
Defect root cause analysis, Андрей ТитаренкоDefect root cause analysis, Андрей Титаренко
Defect root cause analysis, Андрей Титаренко
 
Wso2con test-automation
Wso2con test-automationWso2con test-automation
Wso2con test-automation
 
End to end testing - strategies
End to end testing - strategiesEnd to end testing - strategies
End to end testing - strategies
 
Presentation1
Presentation1Presentation1
Presentation1
 
Management Issues in Test Automation
Management Issues in Test AutomationManagement Issues in Test Automation
Management Issues in Test Automation
 
Regression testing
Regression testingRegression testing
Regression testing
 
ISTQB Advanced Test Manager Training
ISTQB Advanced Test Manager TrainingISTQB Advanced Test Manager Training
ISTQB Advanced Test Manager Training
 
How Automation is Changing The Testing Scene
How Automation is Changing The Testing SceneHow Automation is Changing The Testing Scene
How Automation is Changing The Testing Scene
 
Crawl Walk and Run to Continuous Delivery
Crawl Walk and Run to Continuous DeliveryCrawl Walk and Run to Continuous Delivery
Crawl Walk and Run to Continuous Delivery
 

Viewers also liked

B2 - Integrating on-premises workloads with AWS
B2 - Integrating on-premises workloads with AWSB2 - Integrating on-premises workloads with AWS
B2 - Integrating on-premises workloads with AWSAmazon Web Services
 
Orchestration & Deployment Options for Hybrid Enterprise Environments (ARC310...
Orchestration & Deployment Options for Hybrid Enterprise Environments (ARC310...Orchestration & Deployment Options for Hybrid Enterprise Environments (ARC310...
Orchestration & Deployment Options for Hybrid Enterprise Environments (ARC310...Amazon Web Services
 
Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis
Testing machine learning, learning machine testing. EuroSTAR 2016 Rik MarselisTesting machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis
Testing machine learning, learning machine testing. EuroSTAR 2016 Rik MarselisRik Marselis
 
AWS and VMware: How to Architect and Manage Hybrid Environments
AWS and VMware: How to Architect and Manage Hybrid EnvironmentsAWS and VMware: How to Architect and Manage Hybrid Environments
AWS and VMware: How to Architect and Manage Hybrid EnvironmentsRightScale
 
AWS Summit Stockholm 2014 – B3 – Integrating on-premises workloads with AWS
AWS Summit Stockholm 2014 – B3 – Integrating on-premises workloads with AWSAWS Summit Stockholm 2014 – B3 – Integrating on-premises workloads with AWS
AWS Summit Stockholm 2014 – B3 – Integrating on-premises workloads with AWSAmazon Web Services
 
ATAGTR2017 Machine Learning telepathy for Shift Right approach of testing
ATAGTR2017 Machine Learning telepathy for Shift Right approach of testingATAGTR2017 Machine Learning telepathy for Shift Right approach of testing
ATAGTR2017 Machine Learning telepathy for Shift Right approach of testingAgile Testing Alliance
 
Disruptive technologies that will change aviation in the coming years
Disruptive technologies that will change aviation in the coming yearsDisruptive technologies that will change aviation in the coming years
Disruptive technologies that will change aviation in the coming yearsThoughtworks
 
Machine Learning on Big Data
Machine Learning on Big DataMachine Learning on Big Data
Machine Learning on Big DataMax Lin
 
AI for IA's: Machine Learning Demystified at IA Summit 2017 - IAS17
AI for IA's: Machine Learning Demystified at IA Summit 2017 - IAS17AI for IA's: Machine Learning Demystified at IA Summit 2017 - IAS17
AI for IA's: Machine Learning Demystified at IA Summit 2017 - IAS17Carol Smith
 

Viewers also liked (10)

The Snowball Effect
The Snowball EffectThe Snowball Effect
The Snowball Effect
 
B2 - Integrating on-premises workloads with AWS
B2 - Integrating on-premises workloads with AWSB2 - Integrating on-premises workloads with AWS
B2 - Integrating on-premises workloads with AWS
 
Orchestration & Deployment Options for Hybrid Enterprise Environments (ARC310...
Orchestration & Deployment Options for Hybrid Enterprise Environments (ARC310...Orchestration & Deployment Options for Hybrid Enterprise Environments (ARC310...
Orchestration & Deployment Options for Hybrid Enterprise Environments (ARC310...
 
Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis
Testing machine learning, learning machine testing. EuroSTAR 2016 Rik MarselisTesting machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis
Testing machine learning, learning machine testing. EuroSTAR 2016 Rik Marselis
 
AWS and VMware: How to Architect and Manage Hybrid Environments
AWS and VMware: How to Architect and Manage Hybrid EnvironmentsAWS and VMware: How to Architect and Manage Hybrid Environments
AWS and VMware: How to Architect and Manage Hybrid Environments
 
AWS Summit Stockholm 2014 – B3 – Integrating on-premises workloads with AWS
AWS Summit Stockholm 2014 – B3 – Integrating on-premises workloads with AWSAWS Summit Stockholm 2014 – B3 – Integrating on-premises workloads with AWS
AWS Summit Stockholm 2014 – B3 – Integrating on-premises workloads with AWS
 
ATAGTR2017 Machine Learning telepathy for Shift Right approach of testing
ATAGTR2017 Machine Learning telepathy for Shift Right approach of testingATAGTR2017 Machine Learning telepathy for Shift Right approach of testing
ATAGTR2017 Machine Learning telepathy for Shift Right approach of testing
 
Disruptive technologies that will change aviation in the coming years
Disruptive technologies that will change aviation in the coming yearsDisruptive technologies that will change aviation in the coming years
Disruptive technologies that will change aviation in the coming years
 
Machine Learning on Big Data
Machine Learning on Big DataMachine Learning on Big Data
Machine Learning on Big Data
 
AI for IA's: Machine Learning Demystified at IA Summit 2017 - IAS17
AI for IA's: Machine Learning Demystified at IA Summit 2017 - IAS17AI for IA's: Machine Learning Demystified at IA Summit 2017 - IAS17
AI for IA's: Machine Learning Demystified at IA Summit 2017 - IAS17
 

Similar to Testing in the Age of Machine Learning

supervised and unsupervised learning
supervised and unsupervised learningsupervised and unsupervised learning
supervised and unsupervised learningshivani saluja
 
Presentation slides 2
Presentation slides 2Presentation slides 2
Presentation slides 2HanimHanem
 
AzureML – zero to hero
AzureML – zero to heroAzureML – zero to hero
AzureML – zero to heroGovind Kanshi
 
The path to be a data scientist
The path to be a data scientistThe path to be a data scientist
The path to be a data scientistPoo Kuan Hoong
 
Qualitative and quantitative analysis
Qualitative and quantitative analysisQualitative and quantitative analysis
Qualitative and quantitative analysisNellie Deutsch (Ed.D)
 
LETS PUBLISH WITH MORE RELIABLE & PRESENTABLE MODELLING.pptx
LETS PUBLISH WITH MORE RELIABLE & PRESENTABLE MODELLING.pptxLETS PUBLISH WITH MORE RELIABLE & PRESENTABLE MODELLING.pptx
LETS PUBLISH WITH MORE RELIABLE & PRESENTABLE MODELLING.pptxshamsul2010
 
Machine learning project_promotion
Machine learning project_promotionMachine learning project_promotion
Machine learning project_promotionkahhuey
 
Data Collection and Analysis Tools
Data Collection and Analysis ToolsData Collection and Analysis Tools
Data Collection and Analysis ToolsCaren Gamboa
 
2018-Sogeti-TestExpo-Intelligent_Predictive_Models.pptx
2018-Sogeti-TestExpo-Intelligent_Predictive_Models.pptx2018-Sogeti-TestExpo-Intelligent_Predictive_Models.pptx
2018-Sogeti-TestExpo-Intelligent_Predictive_Models.pptxMinh Nguyen
 
Advancing Testing Program Maturity in your organization
Advancing Testing Program Maturity in your organizationAdvancing Testing Program Maturity in your organization
Advancing Testing Program Maturity in your organizationRamkumar Ravichandran
 
Machine learning: A Walk Through School Exams
Machine learning: A Walk Through School ExamsMachine learning: A Walk Through School Exams
Machine learning: A Walk Through School ExamsRamsha Ijaz
 
EDUC5103 7th Adobe Connect Session Presentation (March 30, 2016)
EDUC5103 7th Adobe Connect Session Presentation (March 30, 2016)EDUC5103 7th Adobe Connect Session Presentation (March 30, 2016)
EDUC5103 7th Adobe Connect Session Presentation (March 30, 2016)Robert Power
 
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)MAHIRA
 
Data+Science+in+Python+-+Data+Prep+&+EDA.pdf
Data+Science+in+Python+-+Data+Prep+&+EDA.pdfData+Science+in+Python+-+Data+Prep+&+EDA.pdf
Data+Science+in+Python+-+Data+Prep+&+EDA.pdfneelakandan2001kpm
 
How to find new ways to add value to your audits
How to find new ways to add value to your auditsHow to find new ways to add value to your audits
How to find new ways to add value to your auditsCaseWare IDEA
 

Similar to Testing in the Age of Machine Learning (20)

1030 track1 bennett
1030 track1 bennett1030 track1 bennett
1030 track1 bennett
 
supervised and unsupervised learning
supervised and unsupervised learningsupervised and unsupervised learning
supervised and unsupervised learning
 
Presentation slides 2
Presentation slides 2Presentation slides 2
Presentation slides 2
 
AzureML – zero to hero
AzureML – zero to heroAzureML – zero to hero
AzureML – zero to hero
 
The path to be a data scientist
The path to be a data scientistThe path to be a data scientist
The path to be a data scientist
 
Introduction to Machine Learning
Introduction to Machine LearningIntroduction to Machine Learning
Introduction to Machine Learning
 
Qualitative and quantitative analysis
Qualitative and quantitative analysisQualitative and quantitative analysis
Qualitative and quantitative analysis
 
Fie2014 guenaga etal
Fie2014 guenaga etalFie2014 guenaga etal
Fie2014 guenaga etal
 
Datascience methodology
Datascience methodologyDatascience methodology
Datascience methodology
 
LETS PUBLISH WITH MORE RELIABLE & PRESENTABLE MODELLING.pptx
LETS PUBLISH WITH MORE RELIABLE & PRESENTABLE MODELLING.pptxLETS PUBLISH WITH MORE RELIABLE & PRESENTABLE MODELLING.pptx
LETS PUBLISH WITH MORE RELIABLE & PRESENTABLE MODELLING.pptx
 
Machine learning project_promotion
Machine learning project_promotionMachine learning project_promotion
Machine learning project_promotion
 
Data Collection and Analysis Tools
Data Collection and Analysis ToolsData Collection and Analysis Tools
Data Collection and Analysis Tools
 
2018-Sogeti-TestExpo-Intelligent_Predictive_Models.pptx
2018-Sogeti-TestExpo-Intelligent_Predictive_Models.pptx2018-Sogeti-TestExpo-Intelligent_Predictive_Models.pptx
2018-Sogeti-TestExpo-Intelligent_Predictive_Models.pptx
 
Advancing Testing Program Maturity in your organization
Advancing Testing Program Maturity in your organizationAdvancing Testing Program Maturity in your organization
Advancing Testing Program Maturity in your organization
 
Machine learning: A Walk Through School Exams
Machine learning: A Walk Through School ExamsMachine learning: A Walk Through School Exams
Machine learning: A Walk Through School Exams
 
Learning Analytics
Learning AnalyticsLearning Analytics
Learning Analytics
 
EDUC5103 7th Adobe Connect Session Presentation (March 30, 2016)
EDUC5103 7th Adobe Connect Session Presentation (March 30, 2016)EDUC5103 7th Adobe Connect Session Presentation (March 30, 2016)
EDUC5103 7th Adobe Connect Session Presentation (March 30, 2016)
 
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
MACHINE LEARNING PRESENTATION (ARTIFICIAL INTELLIGENCE)
 
Data+Science+in+Python+-+Data+Prep+&+EDA.pdf
Data+Science+in+Python+-+Data+Prep+&+EDA.pdfData+Science+in+Python+-+Data+Prep+&+EDA.pdf
Data+Science+in+Python+-+Data+Prep+&+EDA.pdf
 
How to find new ways to add value to your audits
How to find new ways to add value to your auditsHow to find new ways to add value to your audits
How to find new ways to add value to your audits
 

More from vinaya muralidharan

10 surprising reasons your agile transformation is stuck
10 surprising reasons your agile transformation is stuck10 surprising reasons your agile transformation is stuck
10 surprising reasons your agile transformation is stuckvinaya muralidharan
 
Does your product backlog include these
Does your product backlog include theseDoes your product backlog include these
Does your product backlog include thesevinaya muralidharan
 
An enterprise's journey towards agility
An enterprise's journey towards agility   An enterprise's journey towards agility
An enterprise's journey towards agility vinaya muralidharan
 

More from vinaya muralidharan (7)

10 surprising reasons your agile transformation is stuck
10 surprising reasons your agile transformation is stuck10 surprising reasons your agile transformation is stuck
10 surprising reasons your agile transformation is stuck
 
Does your product backlog include these
Does your product backlog include theseDoes your product backlog include these
Does your product backlog include these
 
Team formation considerations
Team formation considerationsTeam formation considerations
Team formation considerations
 
Bad things hide in the dark
Bad things hide in the darkBad things hide in the dark
Bad things hide in the dark
 
Scrumban recipe
Scrumban recipe Scrumban recipe
Scrumban recipe
 
An enterprise's journey towards agility
An enterprise's journey towards agility   An enterprise's journey towards agility
An enterprise's journey towards agility
 
Evolving to agile testing
Evolving to agile testingEvolving to agile testing
Evolving to agile testing
 

Recently uploaded

WSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open Source
WSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open SourceWSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open Source
WSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open SourceWSO2
 
WSO2CON 2024 - WSO2's Digital Transformation Journey with Choreo: A Platforml...
WSO2CON 2024 - WSO2's Digital Transformation Journey with Choreo: A Platforml...WSO2CON 2024 - WSO2's Digital Transformation Journey with Choreo: A Platforml...
WSO2CON 2024 - WSO2's Digital Transformation Journey with Choreo: A Platforml...WSO2
 
WSO2CON 2024 Slides - Open Source to SaaS
WSO2CON 2024 Slides - Open Source to SaaSWSO2CON 2024 Slides - Open Source to SaaS
WSO2CON 2024 Slides - Open Source to SaaSWSO2
 
tonesoftg
tonesoftgtonesoftg
tonesoftglanshi9
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisamasabamasaba
 
%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein
%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein
%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfonteinmasabamasaba
 
What Goes Wrong with Language Definitions and How to Improve the Situation
What Goes Wrong with Language Definitions and How to Improve the SituationWhat Goes Wrong with Language Definitions and How to Improve the Situation
What Goes Wrong with Language Definitions and How to Improve the SituationJuha-Pekka Tolvanen
 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...Shane Coughlan
 
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...masabamasaba
 
WSO2Con2024 - WSO2's IAM Vision: Identity-Led Digital Transformation
WSO2Con2024 - WSO2's IAM Vision: Identity-Led Digital TransformationWSO2Con2024 - WSO2's IAM Vision: Identity-Led Digital Transformation
WSO2Con2024 - WSO2's IAM Vision: Identity-Led Digital TransformationWSO2
 
WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...
WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...
WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...WSO2
 
WSO2CON2024 - It's time to go Platformless
WSO2CON2024 - It's time to go PlatformlessWSO2CON2024 - It's time to go Platformless
WSO2CON2024 - It's time to go PlatformlessWSO2
 
%in Benoni+277-882-255-28 abortion pills for sale in Benoni
%in Benoni+277-882-255-28 abortion pills for sale in Benoni%in Benoni+277-882-255-28 abortion pills for sale in Benoni
%in Benoni+277-882-255-28 abortion pills for sale in Benonimasabamasaba
 
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...masabamasaba
 
%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in sowetomasabamasaba
 
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...WSO2
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrainmasabamasaba
 
Artyushina_Guest lecture_YorkU CS May 2024.pptx
Artyushina_Guest lecture_YorkU CS May 2024.pptxArtyushina_Guest lecture_YorkU CS May 2024.pptx
Artyushina_Guest lecture_YorkU CS May 2024.pptxAnnaArtyushina1
 
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...WSO2
 

Recently uploaded (20)

WSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open Source
WSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open SourceWSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open Source
WSO2CON 2024 - Freedom First—Unleashing Developer Potential with Open Source
 
WSO2CON 2024 - WSO2's Digital Transformation Journey with Choreo: A Platforml...
WSO2CON 2024 - WSO2's Digital Transformation Journey with Choreo: A Platforml...WSO2CON 2024 - WSO2's Digital Transformation Journey with Choreo: A Platforml...
WSO2CON 2024 - WSO2's Digital Transformation Journey with Choreo: A Platforml...
 
WSO2CON 2024 Slides - Open Source to SaaS
WSO2CON 2024 Slides - Open Source to SaaSWSO2CON 2024 Slides - Open Source to SaaS
WSO2CON 2024 Slides - Open Source to SaaS
 
tonesoftg
tonesoftgtonesoftg
tonesoftg
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
 
%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein
%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein
%in Stilfontein+277-882-255-28 abortion pills for sale in Stilfontein
 
What Goes Wrong with Language Definitions and How to Improve the Situation
What Goes Wrong with Language Definitions and How to Improve the SituationWhat Goes Wrong with Language Definitions and How to Improve the Situation
What Goes Wrong with Language Definitions and How to Improve the Situation
 
Abortion Pill Prices Tembisa [(+27832195400*)] 🏥 Women's Abortion Clinic in T...
Abortion Pill Prices Tembisa [(+27832195400*)] 🏥 Women's Abortion Clinic in T...Abortion Pill Prices Tembisa [(+27832195400*)] 🏥 Women's Abortion Clinic in T...
Abortion Pill Prices Tembisa [(+27832195400*)] 🏥 Women's Abortion Clinic in T...
 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
 
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
%+27788225528 love spells in Huntington Beach Psychic Readings, Attraction sp...
 
WSO2Con2024 - WSO2's IAM Vision: Identity-Led Digital Transformation
WSO2Con2024 - WSO2's IAM Vision: Identity-Led Digital TransformationWSO2Con2024 - WSO2's IAM Vision: Identity-Led Digital Transformation
WSO2Con2024 - WSO2's IAM Vision: Identity-Led Digital Transformation
 
WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...
WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...
WSO2CON 2024 - API Management Usage at La Poste and Its Impact on Business an...
 
WSO2CON2024 - It's time to go Platformless
WSO2CON2024 - It's time to go PlatformlessWSO2CON2024 - It's time to go Platformless
WSO2CON2024 - It's time to go Platformless
 
%in Benoni+277-882-255-28 abortion pills for sale in Benoni
%in Benoni+277-882-255-28 abortion pills for sale in Benoni%in Benoni+277-882-255-28 abortion pills for sale in Benoni
%in Benoni+277-882-255-28 abortion pills for sale in Benoni
 
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
%+27788225528 love spells in Knoxville Psychic Readings, Attraction spells,Br...
 
%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto%in Soweto+277-882-255-28 abortion pills for sale in soweto
%in Soweto+277-882-255-28 abortion pills for sale in soweto
 
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
WSO2CON 2024 - Cloud Native Middleware: Domain-Driven Design, Cell-Based Arch...
 
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
%in Bahrain+277-882-255-28 abortion pills for sale in Bahrain
 
Artyushina_Guest lecture_YorkU CS May 2024.pptx
Artyushina_Guest lecture_YorkU CS May 2024.pptxArtyushina_Guest lecture_YorkU CS May 2024.pptx
Artyushina_Guest lecture_YorkU CS May 2024.pptx
 
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
WSO2Con2024 - From Code To Cloud: Fast Track Your Cloud Native Journey with C...
 

Testing in the Age of Machine Learning

  • 1. @vinaya1980 @hrishikarekar TESTING IN THE AGE OF MACHINE LEARNING March 2016
  • 2. https://www.youtube.com/watch?v=DCgHsxISE0Q W H E R E A R E W E H E A D E D httpsweforum.org/agenda/2017/01/worried- about-ai-taking-your-job-its-already-happening-in- japan?utm_content=buffera14af&utm_medium=s ocial&utm_source=twitter.com&utm_campaign=b uffer
  • 3. THE WORLD OF ARTIFICIAL INTELLIGENCE NLP Neural Networks MACHINE LEARNING DEEP LEARNING …..
  • 4. THE FUTURE IS ALREADY HERE Google RankBrain Assistants
  • 5. HOW DOES IT WORK Supervised • Labelled data • Given new data, predict outcome • Classification Unsupervised • No labels • Find hidden structures • Clustering Reinforcement • Decision process • Actions are rewarded or punished • Learns to optimize rewards
  • 7. SUPERVISED LEARNING - CLASSIFCATION http://www.mikedeff.in/MLIntro.PNG
  • 8. INTO THE REALM OF PROBABILITIES Y = f ( x ) Y ≈ f ( x ) What is scrum ? { "Prediction": { "details": { "Algorithm": "SGD", "PredictiveModelType": "MULTICLASS" }, "predictedLabel": "definition", "predictedScores": { "advantages": 0.0001860455668065697, "characteristics": 0.00006915141420904547, "compare": 0.00017757616296876222, "definition": 0.9970965385437012, "disadvantages": 0.0000534967657586094, } } } Can you tell me about scrum ? { "Prediction": { "details": { "Algorithm": "SGD", "PredictiveModelType": "MULTICLASS" }, "predictedLabel": "definition", "predictedScores": { "advantages": 0.01977257989346981, "characteristics": 0.022757112979888916, "compare": 0.008386141620576382, "definition": 0.21092116832733154, "disadvantages": 0.04002799838781357 } } }
  • 9. TOLERANCE LEVELS Y ≈ f ( x ) Know the probability that is within acceptable limits
  • 10. EVALUATE WITH DIFFERENT MODELS Evaluate against a set of algorithms to iterate towards a model that’s closest representation and for further tuning https://s3.amazonaws.com/MLMastery/MachineLearningAlgorithms.png?__s=h4reg8jqwyg4sz3bzdqf
  • 11. EVALUATION – DATA SET APPROACHES Random split • 70% train, 30% test K-fold cross validation Split into 3 datasets • #1 Train on 1 and 2, test on 3 • #2 Train on 2 and 3, test on 1 • #3 Train on 1 and 3, test on 2 Never use the same dataset for training and evaluating
  • 12. ITERATIVE – LEARNING PROCESS Be prepared to throw the model and start again 
  • 13. MODEL ACCURACY - CONFUSION MATRIX Strive for better models, not 100% accurate.
  • 15. MODEL IS AS GOOD AS THE TRAINING DATA If all of the algorithms perform poorly, • it maybe worth considering if there is a lack of learning structure in the data set • some transformation needed to make the structure more learnable • remove unnecessary noise - stop words are typically removed because they cause unnecessary noise)
  • 16. SUMMARY Machine Learning applications demand a shift in testing approach • Use objective acceptance levels to evaluate the application • Express test outcomes in statistical terms • Have a high level understanding of the underlying working of the application