SlideShare une entreprise Scribd logo
1  sur  18
Enterprise DL - Accelerating Deep
Learning Solutions to Production
Aditya Bhattacharya
Lead ML Engineer, West Pharmaceuticals
AI Researcher, MUST Research
About Me My Associations
My Interests
• Lead ML Engineer, West Pharmaceuticals
• AI Researcher, MUST Research
- ADITYA BHATTACHARYA
Vision Text Speech
Objectives of this discussion
Discussions on accelerating DL solutions from notebook or research
environment to production environment
Discussions on making DL solutions scalable and sustainable
?
Target Audience
Software Engineers
Data Engineers
Data Scientists
ML/DL Engineers
AI Researchers
AI Enthusiast
Topics to be discussed
• Typical Data Science Workflow and impact of deep learning solutions
• Why do we need a scalable solution?
• Importance of Process Pipelines
• Importance of an API Layer and User Interface for a scalable solution
• Deep Learning As A Service
• How to make the solution sustainable?
• Importance of Monitoring Layer and Model Performance Metrics
• Feedback mechanism based on confidence interval
Typical Data Science Workflow
1. Business Understanding
2. Data Mining/Collection Process
3. Data Cleaning
4. Exploratory Data Analysis
5. Feature Engineering
6. Predictive Modelling
7. Data Visualization and Model Metrics
Impact of deep learning solutions
Why do we go for DL solution knowing some of its drawbacks?
Why not classical ML approach?
• Classical ML approaches requires a lot of research on the dataset and efforts for
feature engineering
• When dealing with unstructured data, classical ML techniques require a lot of
cleaner dataset for higher accuracy
• Accuracy of the models are usually not good enough with classical ML approach
and not comparable with human level performance
In short,
DL techniques are far more accurate and reliable and easier to implement
particularly with unstructured data.
Image Generation
Image Classification Flow
Neural Style Transfer
Neural Network
Why do we need a scalable solution?
• All organizations invest a lot on data science, machine learning and deep
learning based research to improve their internal process, enhance their
external experience and improve their existing products and solutions.
• All organization want to make data and analytics driven progress.
• Deep Learning and AI solutions will become a basic expectation of all digital
products and services in the near future.
Hence DL solutions should be moved from research environment to production
environment and should be baked seamlessly within products and services.
Scalable Solution Flow
User Interface Layer
Middleware
API Layer
Analytics LayerData Layer
Process Pipelines
• Data Pipeline –
For better accuracy, all DL models require continuous flow of high volume of data at high velocity.
So, the analytics layer, requires a well established data pipeline for continuous synchronization of
data from the data layer. Also, the data layer can have multiple data sources (both structured as well
as unstructured), so continuous data flow to the analytics layer can only be achieved using data
pipelines.
Process Pipelines
• Deployment Pipeline:
The output of the analytics layer is usually the predictive model in case of a deep learning solution (which is
nothing but a file containing either the learned weights and biases of the trained model or the model
configurations). Now these trained model “files” should be stored in a cloud based storage, so that next time,
retraining process is not required. This is done through deployment pipelines.
• Application Integration Pipelines:
This is typically the API endpoints that can access the model “files” and generate predictions or results on the
run-time when called.
Deep Learning As A Service
DL as a Service will only be possible through API endpoints that any
application can consume
• Importance of exposing model results through API
• The API Layer makes sure that there is no tight coupling between the analytics layer
and the application layer
• Any time, the model can be re-trained or updated, and still the running service in
production will not get affected.
• Importance of a user interface to consume the service
• An AI product is incomplete without an user interface which can tap the API endpoints
and fetch results from the analytics layer.
• The User Interface can be a hardware interface, software interface or even now voice
interface!
Does it end here?
?
Sustainable Solution
• Monitoring Layer
• Model Performance at Production
 Performance Evaluation Metrics
 Model Versioning
 Confidence Intervals
• Feedback Layer
• Rule Based Actions Triggered based on production metrics
 Over-fitting or under-fitting problem
 Re-train model with more data
 Hyper Parameter Tuning
 Improvement in Feature Engineering
 Cost and resource optimization
 Scrap off the model and build a new one!
Monitoring Layer
Model Performance at Production
oPerformance Evaluation Metrics
Accuracy
Precision and Recall
F1-score
AUC – ROC Score
(Which one to consider?)
oModel Versioning – How to keep track of historical model performance?
oConfidence Intervals – Deciding the threshold metric score based on which the feedback loop
functions
oA/B Testing – Statistical comparison between different versions of the model at production
Monitoring
Layer
Model Version Storage Link
AUC
Score
Confidence
Interval
Deployment
Date
CNN_Simple_v1 www.mycloudstoragelink.com 0.75 (-0.1, 0.1) 01-01-2020
LeNet_5_v1 www.mycloudstoragelink.com 0.80 (-0.05, 0.05) 01-02-2020
LeNet_5_v2 www.mycloudstoragelink.com 0.82 (-0.05, 0.05) 01-03-2020
ResNet_v1 www.mycloudstoragelink.com 0.95 (-0.02, 0.02) 01-04-2020
Feedback Layer
Why do we need a feedback loop?
• Whenever the production metric score falls below the confidence
interval, there has to be a feedback mechanism to trigger certain
necessary actions
Feedback
Layer
Time
Accuracy
Max
Within CI
The model performance is expected to vary and
even gradually decrease over time
Typical feedback actions to improve robustness of model:
 Over-fitting or under-fitting problem
 Re-train model with more data
 Hyper Parameter Tuning
 Improvement in Feature Engineering
 Cost and resource optimization
 Scrap off the model and build a new one!
The complete picture
User Interface Layer
Middleware
API Layer
Analytics LayerData Layer
Monitoring
Layer
Feedback
Layer
• Lead ML Engineer,
West Pharmaceuticals
• AI Researcher, MUST Research
- ADITYA BHATTACHARYA
Questions?
- Want to connect over LinkedIn ?
- Or email me at: aditya.bhattacharya2016@gmail.com

Contenu connexe

Tendances

Automatic Model Documentation with H2O
Automatic Model Documentation with H2OAutomatic Model Documentation with H2O
Automatic Model Documentation with H2O
Sri Ambati
 

Tendances (20)

Introduction to ML.NET
Introduction to ML.NETIntroduction to ML.NET
Introduction to ML.NET
 
Machine Learning system architecture – Microsoft Translator, a Case Study : ...
Machine Learning system architecture – Microsoft Translator, a Case Study :  ...Machine Learning system architecture – Microsoft Translator, a Case Study :  ...
Machine Learning system architecture – Microsoft Translator, a Case Study : ...
 
Machine Learning With ML.NET
Machine Learning With ML.NETMachine Learning With ML.NET
Machine Learning With ML.NET
 
Guiding through a typical Machine Learning Pipeline
Guiding through a typical Machine Learning PipelineGuiding through a typical Machine Learning Pipeline
Guiding through a typical Machine Learning Pipeline
 
201906 02 Introduction to AutoML with ML.NET 1.0
201906 02 Introduction to AutoML with ML.NET 1.0201906 02 Introduction to AutoML with ML.NET 1.0
201906 02 Introduction to AutoML with ML.NET 1.0
 
Introduction to Azure machine learning
Introduction to Azure machine learningIntroduction to Azure machine learning
Introduction to Azure machine learning
 
Interpretable machine learning
Interpretable machine learningInterpretable machine learning
Interpretable machine learning
 
Insider's introduction to microsoft azure machine learning: 201411 Seattle Bu...
Insider's introduction to microsoft azure machine learning: 201411 Seattle Bu...Insider's introduction to microsoft azure machine learning: 201411 Seattle Bu...
Insider's introduction to microsoft azure machine learning: 201411 Seattle Bu...
 
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIMEUnified Approach to Interpret Machine Learning Model: SHAP + LIME
Unified Approach to Interpret Machine Learning Model: SHAP + LIME
 
Azure Machine Learning
Azure Machine LearningAzure Machine Learning
Azure Machine Learning
 
Introduction to Auto ML
Introduction to Auto MLIntroduction to Auto ML
Introduction to Auto ML
 
Introduction to Azure Machine Learning
Introduction to Azure Machine LearningIntroduction to Azure Machine Learning
Introduction to Azure Machine Learning
 
Rsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible PipelineRsqrd AI: How to Design a Reliable and Reproducible Pipeline
Rsqrd AI: How to Design a Reliable and Reproducible Pipeline
 
Ai use cases
Ai use casesAi use cases
Ai use cases
 
Azure Machine Learning 101
Azure Machine Learning 101Azure Machine Learning 101
Azure Machine Learning 101
 
Ferruzza g automl deck
Ferruzza g   automl deckFerruzza g   automl deck
Ferruzza g automl deck
 
Data Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAMLData Workflows for Machine Learning - Seattle DAML
Data Workflows for Machine Learning - Seattle DAML
 
Explainable AI - making ML and DL models more interpretable
Explainable AI - making ML and DL models more interpretableExplainable AI - making ML and DL models more interpretable
Explainable AI - making ML and DL models more interpretable
 
Automatic Model Documentation with H2O
Automatic Model Documentation with H2OAutomatic Model Documentation with H2O
Automatic Model Documentation with H2O
 
Towards a Comprehensive Machine Learning Benchmark
Towards a Comprehensive Machine Learning BenchmarkTowards a Comprehensive Machine Learning Benchmark
Towards a Comprehensive Machine Learning Benchmark
 

Similaire à Aditya Bhattacharya - Enterprise DL - Accelerating Deep Learning Solutions to Production

Engineering_Campus_Presentation_2022 (1)-compressed.pptx
Engineering_Campus_Presentation_2022 (1)-compressed.pptxEngineering_Campus_Presentation_2022 (1)-compressed.pptx
Engineering_Campus_Presentation_2022 (1)-compressed.pptx
Manikaahuja4
 
Analyti x mapping manager product overview presentation
Analyti x mapping manager product overview presentationAnalyti x mapping manager product overview presentation
Analyti x mapping manager product overview presentation
AnalytixDataServices
 
How to Automate your Enterprise Application / ERP Testing
How to Automate your  Enterprise Application / ERP TestingHow to Automate your  Enterprise Application / ERP Testing
How to Automate your Enterprise Application / ERP Testing
RTTS
 
Feature Store as a Data Foundation for Machine Learning
Feature Store as a Data Foundation for Machine LearningFeature Store as a Data Foundation for Machine Learning
Feature Store as a Data Foundation for Machine Learning
Provectus
 
Software engineering practices for the data science and machine learning life...
Software engineering practices for the data science and machine learning life...Software engineering practices for the data science and machine learning life...
Software engineering practices for the data science and machine learning life...
DataWorks Summit
 
Machine Learning Models in Production
Machine Learning Models in ProductionMachine Learning Models in Production
Machine Learning Models in Production
DataWorks Summit
 

Similaire à Aditya Bhattacharya - Enterprise DL - Accelerating Deep Learning Solutions to Production (20)

Experimentation to Industrialization: Implementing MLOps
Experimentation to Industrialization: Implementing MLOpsExperimentation to Industrialization: Implementing MLOps
Experimentation to Industrialization: Implementing MLOps
 
Global ai conf_final
Global ai conf_finalGlobal ai conf_final
Global ai conf_final
 
DevOps for Machine Learning overview en-us
DevOps for Machine Learning overview en-usDevOps for Machine Learning overview en-us
DevOps for Machine Learning overview en-us
 
Aviana-Nrit BI.ppt
Aviana-Nrit BI.pptAviana-Nrit BI.ppt
Aviana-Nrit BI.ppt
 
MLOps and Data Quality: Deploying Reliable ML Models in Production
MLOps and Data Quality: Deploying Reliable ML Models in ProductionMLOps and Data Quality: Deploying Reliable ML Models in Production
MLOps and Data Quality: Deploying Reliable ML Models in Production
 
Engineering_Campus_Presentation_2022 (1)-compressed.pptx
Engineering_Campus_Presentation_2022 (1)-compressed.pptxEngineering_Campus_Presentation_2022 (1)-compressed.pptx
Engineering_Campus_Presentation_2022 (1)-compressed.pptx
 
Mohamed Sabri: Operationalize machine learning with Kubeflow
Mohamed Sabri: Operationalize machine learning with KubeflowMohamed Sabri: Operationalize machine learning with Kubeflow
Mohamed Sabri: Operationalize machine learning with Kubeflow
 
Mohamed Sabri: Operationalize machine learning with Kubeflow
Mohamed Sabri: Operationalize machine learning with KubeflowMohamed Sabri: Operationalize machine learning with Kubeflow
Mohamed Sabri: Operationalize machine learning with Kubeflow
 
Analyti x mapping manager product overview presentation
Analyti x mapping manager product overview presentationAnalyti x mapping manager product overview presentation
Analyti x mapping manager product overview presentation
 
How to Automate your Enterprise Application / ERP Testing
How to Automate your  Enterprise Application / ERP TestingHow to Automate your  Enterprise Application / ERP Testing
How to Automate your Enterprise Application / ERP Testing
 
Feature Store as a Data Foundation for Machine Learning
Feature Store as a Data Foundation for Machine LearningFeature Store as a Data Foundation for Machine Learning
Feature Store as a Data Foundation for Machine Learning
 
Software engineering practices for the data science and machine learning life...
Software engineering practices for the data science and machine learning life...Software engineering practices for the data science and machine learning life...
Software engineering practices for the data science and machine learning life...
 
MLOps Using MLflow
MLOps Using MLflowMLOps Using MLflow
MLOps Using MLflow
 
Machine Learning Models in Production
Machine Learning Models in ProductionMachine Learning Models in Production
Machine Learning Models in Production
 
It Consulting & Services - Black Basil Technologies
It Consulting & Services  - Black Basil TechnologiesIt Consulting & Services  - Black Basil Technologies
It Consulting & Services - Black Basil Technologies
 
Microsoft DevOps for AI with GoDataDriven
Microsoft DevOps for AI with GoDataDrivenMicrosoft DevOps for AI with GoDataDriven
Microsoft DevOps for AI with GoDataDriven
 
Machine learning in production
Machine learning in productionMachine learning in production
Machine learning in production
 
Machine learning at scale - Webinar By zekeLabs
Machine learning at scale - Webinar By zekeLabsMachine learning at scale - Webinar By zekeLabs
Machine learning at scale - Webinar By zekeLabs
 
[DSC Europe 23] Petar Zecevic - ML in Production on Databricks
[DSC Europe 23] Petar Zecevic - ML in Production on Databricks[DSC Europe 23] Petar Zecevic - ML in Production on Databricks
[DSC Europe 23] Petar Zecevic - ML in Production on Databricks
 
MLOps Virtual Event: Automating ML at Scale
MLOps Virtual Event: Automating ML at ScaleMLOps Virtual Event: Automating ML at Scale
MLOps Virtual Event: Automating ML at Scale
 

Plus de Aditya Bhattacharya

Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023
Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023
Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023
Aditya Bhattacharya
 

Plus de Aditya Bhattacharya (6)

Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023
Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023
Directive Explanations for Monitoring the Risk of Diabetes Onset - ACM IUI 2023
 
ODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AIODSC APAC 2022 - Explainable AI
ODSC APAC 2022 - Explainable AI
 
Time series Segmentation & Anomaly Detection
Time series Segmentation & Anomaly DetectionTime series Segmentation & Anomaly Detection
Time series Segmentation & Anomaly Detection
 
Application of Masked RCNN for segmentation of brain haemorrhage from Compute...
Application of Masked RCNN for segmentation of brain haemorrhage from Compute...Application of Masked RCNN for segmentation of brain haemorrhage from Compute...
Application of Masked RCNN for segmentation of brain haemorrhage from Compute...
 
Aditya Bhattacharya Chest XRay Image Analysis Using Deep Learning
Aditya Bhattacharya Chest XRay Image Analysis Using Deep LearningAditya Bhattacharya Chest XRay Image Analysis Using Deep Learning
Aditya Bhattacharya Chest XRay Image Analysis Using Deep Learning
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathon
 

Dernier

UNIT-V FMM.HYDRAULIC TURBINE - Construction and working
UNIT-V FMM.HYDRAULIC TURBINE - Construction and workingUNIT-V FMM.HYDRAULIC TURBINE - Construction and working
UNIT-V FMM.HYDRAULIC TURBINE - Construction and working
rknatarajan
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Christo Ananth
 
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
dharasingh5698
 
result management system report for college project
result management system report for college projectresult management system report for college project
result management system report for college project
Tonystark477637
 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdf
ankushspencer015
 

Dernier (20)

UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduits
 
UNIT-III FMM. DIMENSIONAL ANALYSIS
UNIT-III FMM.        DIMENSIONAL ANALYSISUNIT-III FMM.        DIMENSIONAL ANALYSIS
UNIT-III FMM. DIMENSIONAL ANALYSIS
 
UNIT-V FMM.HYDRAULIC TURBINE - Construction and working
UNIT-V FMM.HYDRAULIC TURBINE - Construction and workingUNIT-V FMM.HYDRAULIC TURBINE - Construction and working
UNIT-V FMM.HYDRAULIC TURBINE - Construction and working
 
Thermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - VThermal Engineering-R & A / C - unit - V
Thermal Engineering-R & A / C - unit - V
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
 
ONLINE FOOD ORDER SYSTEM PROJECT REPORT.pdf
ONLINE FOOD ORDER SYSTEM PROJECT REPORT.pdfONLINE FOOD ORDER SYSTEM PROJECT REPORT.pdf
ONLINE FOOD ORDER SYSTEM PROJECT REPORT.pdf
 
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 BookingVIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
VIP Call Girls Ankleshwar 7001035870 Whatsapp Number, 24/07 Booking
 
Roadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and RoutesRoadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and Routes
 
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
 
result management system report for college project
result management system report for college projectresult management system report for college project
result management system report for college project
 
Glass Ceramics: Processing and Properties
Glass Ceramics: Processing and PropertiesGlass Ceramics: Processing and Properties
Glass Ceramics: Processing and Properties
 
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...Top Rated  Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdf
 
Double rodded leveling 1 pdf activity 01
Double rodded leveling 1 pdf activity 01Double rodded leveling 1 pdf activity 01
Double rodded leveling 1 pdf activity 01
 
Coefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptxCoefficient of Thermal Expansion and their Importance.pptx
Coefficient of Thermal Expansion and their Importance.pptx
 
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)
 
Thermal Engineering -unit - III & IV.ppt
Thermal Engineering -unit - III & IV.pptThermal Engineering -unit - III & IV.ppt
Thermal Engineering -unit - III & IV.ppt
 
Online banking management system project.pdf
Online banking management system project.pdfOnline banking management system project.pdf
Online banking management system project.pdf
 
VIP Model Call Girls Kothrud ( Pune ) Call ON 8005736733 Starting From 5K to ...
VIP Model Call Girls Kothrud ( Pune ) Call ON 8005736733 Starting From 5K to ...VIP Model Call Girls Kothrud ( Pune ) Call ON 8005736733 Starting From 5K to ...
VIP Model Call Girls Kothrud ( Pune ) Call ON 8005736733 Starting From 5K to ...
 

Aditya Bhattacharya - Enterprise DL - Accelerating Deep Learning Solutions to Production

  • 1. Enterprise DL - Accelerating Deep Learning Solutions to Production Aditya Bhattacharya Lead ML Engineer, West Pharmaceuticals AI Researcher, MUST Research
  • 2. About Me My Associations My Interests • Lead ML Engineer, West Pharmaceuticals • AI Researcher, MUST Research - ADITYA BHATTACHARYA Vision Text Speech
  • 3. Objectives of this discussion Discussions on accelerating DL solutions from notebook or research environment to production environment Discussions on making DL solutions scalable and sustainable ?
  • 4. Target Audience Software Engineers Data Engineers Data Scientists ML/DL Engineers AI Researchers AI Enthusiast
  • 5. Topics to be discussed • Typical Data Science Workflow and impact of deep learning solutions • Why do we need a scalable solution? • Importance of Process Pipelines • Importance of an API Layer and User Interface for a scalable solution • Deep Learning As A Service • How to make the solution sustainable? • Importance of Monitoring Layer and Model Performance Metrics • Feedback mechanism based on confidence interval
  • 6. Typical Data Science Workflow 1. Business Understanding 2. Data Mining/Collection Process 3. Data Cleaning 4. Exploratory Data Analysis 5. Feature Engineering 6. Predictive Modelling 7. Data Visualization and Model Metrics
  • 7. Impact of deep learning solutions Why do we go for DL solution knowing some of its drawbacks? Why not classical ML approach? • Classical ML approaches requires a lot of research on the dataset and efforts for feature engineering • When dealing with unstructured data, classical ML techniques require a lot of cleaner dataset for higher accuracy • Accuracy of the models are usually not good enough with classical ML approach and not comparable with human level performance In short, DL techniques are far more accurate and reliable and easier to implement particularly with unstructured data. Image Generation Image Classification Flow Neural Style Transfer Neural Network
  • 8. Why do we need a scalable solution? • All organizations invest a lot on data science, machine learning and deep learning based research to improve their internal process, enhance their external experience and improve their existing products and solutions. • All organization want to make data and analytics driven progress. • Deep Learning and AI solutions will become a basic expectation of all digital products and services in the near future. Hence DL solutions should be moved from research environment to production environment and should be baked seamlessly within products and services.
  • 9. Scalable Solution Flow User Interface Layer Middleware API Layer Analytics LayerData Layer
  • 10. Process Pipelines • Data Pipeline – For better accuracy, all DL models require continuous flow of high volume of data at high velocity. So, the analytics layer, requires a well established data pipeline for continuous synchronization of data from the data layer. Also, the data layer can have multiple data sources (both structured as well as unstructured), so continuous data flow to the analytics layer can only be achieved using data pipelines.
  • 11. Process Pipelines • Deployment Pipeline: The output of the analytics layer is usually the predictive model in case of a deep learning solution (which is nothing but a file containing either the learned weights and biases of the trained model or the model configurations). Now these trained model “files” should be stored in a cloud based storage, so that next time, retraining process is not required. This is done through deployment pipelines. • Application Integration Pipelines: This is typically the API endpoints that can access the model “files” and generate predictions or results on the run-time when called.
  • 12. Deep Learning As A Service DL as a Service will only be possible through API endpoints that any application can consume • Importance of exposing model results through API • The API Layer makes sure that there is no tight coupling between the analytics layer and the application layer • Any time, the model can be re-trained or updated, and still the running service in production will not get affected. • Importance of a user interface to consume the service • An AI product is incomplete without an user interface which can tap the API endpoints and fetch results from the analytics layer. • The User Interface can be a hardware interface, software interface or even now voice interface!
  • 13. Does it end here? ?
  • 14. Sustainable Solution • Monitoring Layer • Model Performance at Production  Performance Evaluation Metrics  Model Versioning  Confidence Intervals • Feedback Layer • Rule Based Actions Triggered based on production metrics  Over-fitting or under-fitting problem  Re-train model with more data  Hyper Parameter Tuning  Improvement in Feature Engineering  Cost and resource optimization  Scrap off the model and build a new one!
  • 15. Monitoring Layer Model Performance at Production oPerformance Evaluation Metrics Accuracy Precision and Recall F1-score AUC – ROC Score (Which one to consider?) oModel Versioning – How to keep track of historical model performance? oConfidence Intervals – Deciding the threshold metric score based on which the feedback loop functions oA/B Testing – Statistical comparison between different versions of the model at production Monitoring Layer Model Version Storage Link AUC Score Confidence Interval Deployment Date CNN_Simple_v1 www.mycloudstoragelink.com 0.75 (-0.1, 0.1) 01-01-2020 LeNet_5_v1 www.mycloudstoragelink.com 0.80 (-0.05, 0.05) 01-02-2020 LeNet_5_v2 www.mycloudstoragelink.com 0.82 (-0.05, 0.05) 01-03-2020 ResNet_v1 www.mycloudstoragelink.com 0.95 (-0.02, 0.02) 01-04-2020
  • 16. Feedback Layer Why do we need a feedback loop? • Whenever the production metric score falls below the confidence interval, there has to be a feedback mechanism to trigger certain necessary actions Feedback Layer Time Accuracy Max Within CI The model performance is expected to vary and even gradually decrease over time Typical feedback actions to improve robustness of model:  Over-fitting or under-fitting problem  Re-train model with more data  Hyper Parameter Tuning  Improvement in Feature Engineering  Cost and resource optimization  Scrap off the model and build a new one!
  • 17. The complete picture User Interface Layer Middleware API Layer Analytics LayerData Layer Monitoring Layer Feedback Layer
  • 18. • Lead ML Engineer, West Pharmaceuticals • AI Researcher, MUST Research - ADITYA BHATTACHARYA Questions? - Want to connect over LinkedIn ? - Or email me at: aditya.bhattacharya2016@gmail.com