AI in the enterprise
- 1. Powering Up AI in the Enterprise Clarisse Taaffe-Hedglin Executive IT Architect IBM Garage IBM Systems clarisse@us.ibm.com
- 2. Agenda Industry Use cases The AI Ladder and Lifecycle AI at Scale Themes Infrastructure Considerations
- 3. “AI is the fastest-growing workload”* 3 *Forrester Research Inc. “AI Deep Learning Workloads Demand a New Approach to Infrastructure”, by Mike Gualtieri, Christopher Voce, Srividya Sridharan, Michele Goetz, Renee Taylor, May 4, 2018. 3 IBM IT Infrastructure / © 2021 IBM Corporation
- 4. Machine Learning Context REINFORCEMENT LEARNING TRANSFER LEARNING “AI is the automation of automation” – Jensen Huang, GCG 2020
- 5. 5 Enterprise Analytics Modernization: From Data to Actions 010101010101010111100010011001010111 0000000000010101010100000000000 111101011 11000 000000000000 111111 010101 101010 10101010100 Prescriptive What should we do ? Descriptive What Has Happened? Cognitive Learn Dynamically Predictive What Will Happen? ACTION DATA HUMAN INPUTS < < > < > > >
- 6. Predict a Future Event Segment Data / Detect Anomalies Determine optimal quantity, price, resource allocation, or best action Understand Past Activity Discover Insights in Content (text, images, video) Interact in Natural Language Forecast and Budget based on past activity Semi-Supervised Unsupervised Predictive: What will happen? Prescriptive: What should we do? Descriptive: What happened? Planning: What is our Plan? NLP Deep Learning Supervised AI in Common Patterns of Analytics Solving challenges with Data and AI will utilize a combination of these analytics patterns
- 7. § BIG, COMPLEX SYSTEMS § PERSONALIZATION § AUTOMATION § SIMULATING RELATIONSHIPS § VISUAL RECOGNITION § PATTERN DETECTION § CHATBOTS § DESIGN OF EXPERIMENTS § OPTIMIZATION Thescenarios AIcansolvefor today 7 IBM IT Infrastructure / © 2021 IBM Corporation
- 8. Three broad categories of AI Use Cases “Structured” Data Use Cases Computer Vision Use Cases - Big Data (Rows and Columns) - Available AI Software More Accuracy ! This is sort of “Magic” - a deep learning Model is trained to detect and classify objects Natural Language Processing Use Cases - A Model learns to read, hear and “understand” language
- 9. Addressable Markets And Fields For AI RETAIL Recommendation engines, Precision marketing AGRICULTURE Crop yield, Plant disease, Remote sensing LIFE SCIENCES Sequence Analysis, Radiology UTILITIES Smart Meter analysis, Capacity planning $ FINANCIAL SERVICES Risk analysis Fraud detection CUSTOMER SERVICE Chatbots, Helpdesk, Automated Expenses LAW & DEFENSE Threat analysis - social media monitoring RESEARCH Physics Modeling Simulation optimization TRANSPORTATION Optimal traffic flows, Route planning CONSUMER GOODS Sentiment analysis HEALTH CARE Patient sensors, monitoring, EHRs MEDIA/ENTERTAINMENT Advertising effectiveness OIL & GAS Exploration, Sensor analysis AUTOMOTIVE ADAS, Maintenance MANUFACTURING Line inspection, Defect analysis AI and Autonomous Machine Learning will help revolutionized every single industry making us more productive and efficient to do things that today are impossible to do. 9 IBM IT Infrastructure / © 2021 IBM Corporation
- 10. IBM Federal IBM Federal / August 2020 / © 2020 IBM Corporation
- 11. A New Era of Autonomous Ships IBM has partnered with ProMare, a U.K.-based nonprofit research organization on building a fully autonomous Mayflower, built for the 21st Century. The Mayflower will be one of the first self-navigating, full-sized vessels to cross the Atlantic. It will have no captain or crew; instead, it will use IBM AI and Hybrid Cloud technologies to traverse the Atlantic and gather data that will help safeguard the health of the ocean and the industries it supports. The ship will depart Plymouth, England and set sail for Plymouth, MA in the spring of 2021 and will have the ability to operate independently in very challenging environments. IBM Federal / August 2020 / © 2020 IBM Corporation 11
- 12. Scientific Experiments Navigation Systems SatCom / 4G / WiFi Control Center Hybrid Cloud Solution at the Edge Edge Agent Docker / RH Intermittent inbox / outbox Mission management vessel monitoring, planning, status, Cloud AI Captain Ship inbox / outbox Path Optimization: weather, efficiency, analytics Safety Care Kill switch Scientific Teams Public portal Edge Management RH OCP Weather On Premises Mayflower project / Oct 14th / © 2020 Submergence - MSubs - MarineAI - IBM Ship / Edge PowerCPU
- 13. Vision AI Sensors (every second) Structure Rules Engine Evaluate Decide Optim Engine Unstructured To Structured Data Fusion COLREGS 1 to 1 problem MISSION objectives Weather Multiship problem Charts Control Hybrid Cloud and AI Architecture Vessel Dynamic Control / Robotics Command center Data Collection Development Action Vision Dev Rules Dev Optim Dev Edge Mgt Cameras Radar Local Weather AIS intermittent Mayflower project / Oct 14th / © 2020 Submergence - MSubs - MarineAI - IBM Weather Vessel Dynamic Controlc AI Captain
- 14. Manufacturing Hybrid Cloud and AI Architecture Servers GPU / FPGA Storage ( ESS ) Quality Inspection - Very low latency - Device Inference? Equipment Sensors - low latency Plant Optimization - batch Factory location …n Quality Inspection - Very low latency Equipment Sensors - low latency Servers GPU (IC922) Storage ( ESS ) Optimization - batch Factory location 2 Cloud / IOT Quality Inspection - Very low latency - Device Inference? Equipment Sensors - low latency Servers GPU / FPGA Storage ( ESS ) Plant Optimization - batch Factory location 1 . . . . AI Applications and Data Hybrid Cloud - Containers - Cloud Paks Data and meta-data Servers GPU Storage On-Prem Enterprise Systems AI inferencing In Transaction Systems Headquarters Archive AI Model Training 14 IBM IT Infrastructure / © 2021 IBM Corporation
- 15. Data Science Exploration to Production Use Case Exploration Data Science Model Build Use Case Deployment in Production Requires solution architecture Deploy Source: https://papers.nips.cc/paper/5656-hidden-technical-debt-in-machine-learning-systems.pdf Use Case Exploration Data Science Model Build Security, Privacy and Governance
- 16. Modernize to Real Time Payments Access core apps & data via Open APIs Optimize Risk, Pricing with Analytics Stay ahead of money laundering Meet new open banking regulations, add faster payment methods, and simplify transfer of funds across financial institutions. Get rapid access to data and monitor with adaptive rules to detect suspicious activity Leverage container-based microservices and open APIs to integrate mission critical banking data into new cloud native applications. Securely access disparate data and quickly perform complex calculations with vast amounts of data for better insights Banking Innovation Enabled by AI and Hybrid Cloud 16 IBM IT Infrastructure / © 2021 IBM Corporation
- 17. 17 Anti-money laundering solution boundary EVENT SOURCES KNOW YOUR CUSTOMER ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING WORKFLOW CASE MANAGEMENT INVESTIGATION PROCESS Back office Check processing Watch Lists Data warehouse Distributed files Other DATA SOURCE AND TRANSACTION DATA FRAUD PROCESSING SYSTEM TRANSACTION AND EVENT BUS ANTI-MONEY LAUNDERING TRANSACTION MONITORING Transaction labeling models Transaction scoring Anti-money laundering rules Back office Check processing Distributed files Other USER INTERFACE Anti-Money Laundering (AML) Hybrid and AI Architecture 17 IBM IT Infrastructure / © 2021 IBM Corporation
- 18. Data Insight HPC Analysis & Simulation AI Inference & Automation Sensors The Convergence of HPC and AI 18 IBM IT Infrastructure / © 2021 IBM Corporation
- 19. Designing a Formula 1 car is complex. Validating component design is crucial, but testing aerodynamics, either physically or by simulation, is costly.
- 20. …leading to fewer simulations and lower development costs Using IBM Bayesian Optimization Accelerator to automatically predict the next best set of parameters to explore, we can minimize the drag to lift ratio to optimize the design of F1 car components efficiently… Formula 1 Design Exploration using AI and HPC 20 IBM IT Infrastructure / © 2021 IBM Corporation
- 21. Improve application performance & reduce design cycle time BOOST PERFORMANCE Improve analyst productivity, reduce human workload INCREASE PRODUCTIVITY Run critical simulations at resolutions which were too expensive SUPPORT NEW PARADIGMS Achieve design results with less experienced users INCREASE USER EFFICIENCY Reduce costs by performing fewer simulations per design REDUCE COSTS Minimize business dependence upon senior “Expert” level users MINIMIZE DEPENDENCIES Beat the competition to market by significant margins IMPROVE TIME TO MARKET Stop running simulations which don’t advance product design IMPROVE EFFECTIVENESS Bayesian Optimization Accelerator Delivers Business Value 21 IBM IT Infrastructure / © 2021 IBM Corporation
- 22. 22 Machine learning models were trained to act as an HPC surrogate for the physics-based SWAN model An ML/DL model accurately represented the significant wave height field and an SVM model simulated the characteristic period Machine learning models represented the SWAN- simulated wave conditions in less than 1/1000th of the computational time SWAN Model: Physics-based HPC simulation forecasting wave height ML/DL Model: forecast of wave height at comparable accuracy https://arxiv.org/abs/1709.08725 An AI Solution for Highly Accurate Wave Condition Forecasts 22 IBM IT Infrastructure / © 2021 IBM Corporation
- 23. COLLECT - Make data simple and accessible ORGANIZE - Create a trusted analytics foundation ANALYZE - Scale AI everywhere with trust & transparency Data of every type, regardless of where it lives MODERNIZE your data estate for an AI and hybrid multicloud world INFUSE – Operationalize AI across business processes The AI Ladder A prescriptive approach to accelerating the journey to AI AI AI-optimized systems infrastructure 23 IBM IT Infrastructure / © 2021 IBM Corporation
- 24. Unstructured, Landing, Exploration and Archive Operational Data Real-time Data Processing & Analytics Transaction and application data Machine, sensor data Enterprise content Image, geospatial, video Social data Third-party data Information Integration & Governance Data is Prerequisite to AI Risk, Fraud Chat bots, personal assistants Supply Chain Optimization Dynamic Pricing, Recommenders Behavior Modeling Vision, Autonomous Systems
- 25. Public data Anything data system can pull from the outside world for free through web connections, databases, IoT and sensors Proprietary data What private data from the outside world could the system be given permission to use? Purchased data What pre-trained data could the system buy or subscribe to? IBM Skills Academy / © Copyright 2018 IBM Corporation Ground truth Data used to define what the system knows from day one Domain knowledge Data resources that can be used to teach the system to understand and be an expert in a particular field Private data Unique data the creator owns and only shares internally Personal public data What unique data does the creator share with the outside world? Transaction and application data Machine, sensor data Enterprise content Image, geospatial, video Social data Third-party data Available Data Sources
- 26. Enterprise Data Pipeline for AI Insights Out Trained Models, simulations Inference Data In Transient Storage SDS/Cloud Global Ingest Throughput-oriented, globally accessible Cloud ETL High throughput, Random I/O, SSD/Hybrid Archive High scalability, large/sequential I/O HDD Cloud Tape Hadoop / Spark Data Lakes Throughput-oriented Hybrid/HDD ML / DL Prep ⇨ Training ⇨ Inference High throughput, low latency, Random I/O SSD/NVMe Classification & Metadata Tagging High volume, index & auto-tagging zone Fast Ingest / Real-time Analytics High throughput SSD Throughput-oriented, software defined temporary landing zone capacity tier performance tier performance & capacity Tier performance & capacity Tier performance tier capacity tier Fits Traditional and New Use Cases EDGE COLLECT ORGANIZE ANALYZE INSIGHTS INFUSE IBM Spectrum Scale / Storage for AI / © 2020 IBM Corporation
- 27. Metadata-Fueled Data Analysis Large Scale Data Ingest • Scan records at high speed • Live event notifications • Capture system-level tags • Automatic indexing Business-Oriented Data Mapping • Custom data tagging • Content-inspection via APIs • Policy-driven workflows Data Activation • Data movement via APIs • Extensible architecture • Solution Blueprints Data Visualization • Query billions of records in seconds • Multi-faceted search • Drilldown dashboard • Customizable reports
- 28. Common AI Data Considerations Data Compute Legacy Data Stores IoT, Mobile & Sensors Collaboration Partners New Data Ingest Inference Training Preparation Iterative Model training to improve accuracy Champion Challenge r -”Data Center” - At Edge Trained Model § Ease to Massively Scale § High Performance § Tiered / Archive § Secure § High Performance § Metadata Tagging § Single Name Space Low Latency Dev & Inference Stack - Open Source - Stable and Supported - Auditable Productivity Performance Robustness Considerations
- 29. Data and AI Lifecycle in the Enterprise
- 30. AI Model Development Workflow •Data preparation, cleaning, labelling •Model development environment •Runtime environment •Train, deploy and manage models •Business KPI and production metrics •Explainability and fairness Data Engineering and Data Science Team IT Operations Team
- 31. Infrastructure Demands for AI Equipped for volumes of data Flexible storage for a range of data demands Versatile, power-efficient data center accelerators Advanced I/O for minimal latency Scalability and distributed data center capability Inference Powerful data center accelerators with coherence Advanced I/O for high bandwidth and low latency Proven scalability Training Equipped for volumes of data
- 33. • Ease of use • Optimize resources • Scale workload AI Frameworks / Open-Source Libraries AI Tools and Applications AI Software Landscape AI Infrastructure 33 IBM IT Infrastructure / © 2021 IBM Corporation
- 34. OpenPOWER is a technical community dedicated to expanding the the IBM Power architecture ecosystem https://github.com/open-ce Open-CE Minimize time to value for foundational ML/DL packages Provide a flexible source-to-image solution to provide a complete and customizable AI environment.
- 36. Data Data Data Microservices Containerized Workloads Multicloud Provisioning Public Cloud On-prem ises An architecture of loosely coupled data services, easily refactored to create containerized workloads Stand-alone workloads composed of microservices & data that are flexibly deployed, orchestrated and managed Agile provisioning of containerized workloads in multicloud environments and consumption of cloud services Cloud Native Platforms Agility o Efficiency o Cost Savings IBM Cloud Pak for Data
- 37. Hybrid Cloud and AI can help business innovate and transform 37 Think 2020 / DOC ID / Month XX, 2020 / © 2020 IBM Corporation Migrate to Hybrid Cloud Transform the Business Innovate the Business Evolve the IT Landscape with Power Systems 20K+ clients running mission critical workloads on Power Systems. IBM Systems is the engine behind Enterprise. 62% of Power customers prefer cloud deployment by 2021 Innovation is only possible if the IT landscape can evolve leveraging hybrid cloud technologies IBM Systems, IBM Cloud, and IBM Services jointly create hybrid cloud solutions
- 38. Data Pipeline -The data that is feed into models has to be cleaned and structured to produce accurate results Real-Time (vs Batch) - Many AI applications have response times in milli-seconds and in many cases have 100K+ IOT events per second (Latency, Latency, Latency) Scalability - Ability to scale inference engine and manage infrastructure Security - Applications running AI models in the field and back-offices Multi-Tenancy - Multiple business applications leveraging shared infrastructure, Multiple Models per Business Application Tools Proliferation - Analytics, Data/Object Tagging, Model Training and Inferencing Model Management - Continuous Training/Re-Training of Models, AI-DevOps, Ease of Deployment Transparency - Ability to explain decisions A C C U R A C Y Typical AI Inferencing Considerations
- 39. Fairness Explainability Adversarial Robustness Transparency Is it fair? Is it easy to understand? Is it secure? Is it accountable? Pillars of Trusted AI 39 IBM IT Infrastructure / © 2021 IBM Corporation
- 40. Thank You