Industrial Machine Learning (at GE)
4 likes1,236 views
The document discusses the application of industrial machine learning (IML) within the context of artificial intelligence, highlighting opportunities, challenges, and specific applications in the industry. It emphasizes the importance of systems engineering in IML, detailing the complexities of model implementation and the necessity for multi-axis optimizations. Additionally, it showcases specific IML applications in production, with a focus on improving operational efficiency and decision-making in various sectors.
Industrial Machine Learning (at GE)
- 1. Industrial Machine Learning Applied Artificial Intelligence in the New Industrial Revolution, 13 April 2017 (SF) Josh Bloom @profjsb
- 2. COPYRIGHT 2012-2017, WISE.IO INC. • Brief Background/Introduction: Me & Wise.io • Industrial Machine Learning (IML) Opportunities • ML as a Systems Engineering Challenge • IML Applications at GE Agenda
- 3. Teaching ‣ Python Bootcamps 200+ undergrad/grad ‣ Python for Data Science graduate course Industry ‣ML Applications Company Code / Repos Q4’16 CTO, Co-founder Professor, UC Berkeley Research Gordon & Betty Moore Foundation Data-Driven Investigator ‣ Automated Data-driven Discovery & Inference in the Time Domain ‣300+ refereed articles
- 4. COPYRIGHT 2012-2017, WISE.IO INC. “Intelligent applications in Production” Customer Support Product ○Intelligent Routing/Triage ○Response Recommendation ○Auto-Response ○Knowledge-base Deflection ○Federated Search ○Spam Filtering ○Sentiment Prediction ○IoT/proactive support Enhancing Decisions in Human-centric Workflows • Currently serving dozens of customers in production • Our customers: mid-sized, 5k-5M interactions/month, charged on a per ticket basis
- 5. COPYRIGHT 2012-2017, WISE.IO INC. Wise.io @ GE Build & deploy SaaS-based production-grade scalable intelligent IIoT applications for end business users Leveraging the data, horizontal edge-to-cloud platform (Predix), & industry relationships already at GE
- 6. IIoT: Beyond “Smart” Thermostats, Fitbits, and Self-driving cars…
- 7. COPYRIGHT 2012-2017, WISE.IO INC. Consumer Internet Industrial Internet Data Management Day’s worth of Twitter: 500 GB Single flight: 1 TB Connectivity Biggest cell phone complaint: dropped calls Mission critical, rough & remote Device Support Average wearables lifetime: 6 months Lifetime of a Turbine: 20+ years Security Time to Hack most devices: minutes 24/7 Mission Critical Privacy Privacy is no longer a “social norm” - Zuck HIPAA, ITAR, … IIoT: The Internet of Really Important Things
- 8. Industrial Machine Learning as a Systems Challenge
- 9. What are we optimizing for? Component What Algorithm/Model Learning rate, convexity, error bounds, scaling, … + Software/Hardware Accuracy, Memory usage, Disk usage, CPU needs, time to learn, time to predict + Project Staff time to implement, people/ resource costs, reliability, maintainability, experimentability + Consumers direct value, useability, explainability, actionability, security, privacy + Society indirect value, ethics - multi-axis optimizations in a given component - highly coupled optimization considerations between components - myopic view can be costly further up the stack All ML in production is a Systems Challenge
- 10. Copyright 2012-2017, wise.io inc. 10 One ML Algorithmic Trade-Off High Low Low High Interpretability Accuracy Linear/Logistic Regression Naive Bayes Decision Trees SVMs Bagging Boosting Decision Forests Neural Nets Deep Learning Nearest Neighbors Gaussian/ Dirichlet Processes Splines * on real-world data sets Lasso Warning Unscientific & opinionated!
- 11. 11 >$50k Prize <$50k Prize Netflix winning metric best benchmark many teams get within ~few % of optimum so which is easier to put into production? Leaderboard data from Kaggle & Netflix Optimization Metric
- 12. 12 “We evaluated some of the new methods offline but the additional accuracy gains that we measured did not seem to justify the engineering effort needed to bring them into a production environment.” Xavier Amatriain and Justin Basilico (April 2012) On the Prize
- 13. http://research.google.com/pubs/pub43146.html • Complex models erode abstraction boundaries • Data dependencies cost more than code dependencies: weak contracts • System-level Spaghetti • Changing External World “It may be surprising to the academic community to know that only a fraction of the code … is actually doing ‘machine learning’. A mature system might end up being (at most) 5% machine learning code and (at least) 95% glue code.” see also, Bottou (Facebook) ICML
- 14. Prediction API in-houseas a service experimental/sandbox production/scale ready watsonAPI
- 15. Prediction API in-houseas a service experimental/sandbox production/scale ready watsonAPI time & cost to implement cost to maintain
- 16. COPYRIGHT 2012-2017, WISE.IO INC. Wise Architecture: Leveraging Cloud-based Services Services Oriented, Leveraging PaaS Managed Services Microscaling: Dockerized templated workflows for CPU/ GPU build/predict end-points Macro scaling: compute clusters load-balance RESTful contracts between services Build on the AWS stack; Instantiated with terraform End-user Transactional Systems Embedded UI Wise App SDK Use Case Specific Middleware Auth Monitoring/ Alerting Admin Dashboard Reporting Wise Factory Wise Template (Learn/Prediction/Feedback) Transaction DB Model Storage / Management FrontendMiddlewareMLbackend
- 18. Inline Pipeline Inspection Technology ▶ Action
- 19. + seam detected Crack Terabytes of Inspection data Aggregate historic data to enable learning from experience Advanced machine learning generates more accurate insights Surfaced to analysts to improve performance, drive consistency, & repeatability Our Goal: drive Zero-Pipeline-Failure
- 22. The Power of a 1% Gain in Efficiency $27B $30B $63B $66B $90B Rail Aviation Healthcare Power Oil & Gas Source: “Industrial Internet Pushing Boundaries of Minds & Machines” GE, 2012
- 23. Industrial Machine Learning Applied Artificial Intelligence in the New Industrial Revolution, 13 April 2017 (SF) Josh Bloom @profjsb Thanks! (and yes, we’re hiring…)