book

Getting Started with Artificial Intelligence, 2nd Edition

by Tom Markiewicz, Josh Zheng

October 2020

Beginner

83 pages

1h 55m

English

O'Reilly Media, Inc.

Read now

Unlock full access

The Market for Artificial IntelligenceAvoiding an AI WinterArtificial Intelligence, Defined?Artificial IntelligenceMachine LearningDeep LearningApplications in the EnterpriseNext Steps
Overview of NLPThe Components of NLPEntitiesRelationsConceptsKeywordsSemantic RolesCategoriesEmotionSentimentEnterprise Applications of NLPSocial Media AnalysisCustomer SupportBusiness IntelligenceContent Marketing and RecommendationAdditional TopicsHow to Use NLPTraining ModelsChallenges of NLPSummary
What Is a Chatbot?The Rise of ChatbotsNatural Language Processing in the CloudProliferation of Messaging PlatformsNatural Language InterfaceHow to Build a ChatbotThe Messaging ChannelThe BackendChallenges of Building a Successful ChatbotSummary
Capabilities of Computer Vision for the EnterpriseImage Classification and TaggingObject LocalizationCustom ClassifiersHow to Use Computer VisionComputer Vision on Mobile DevicesBest PracticesQuality Training ImagesUse CasesSatellite ImagingVideo Search in Surveillance and EntertainmentAdditional Examples: Social Media and InsuranceExisting Challenges in Computer VisionImplementing a Computer Vision SolutionSummary
Preparing for a Data PipelineSourcing Big DataStorage: Apache HadoopHadoop as a Data LakeDiscovery: Apache SparkSpark Versus MapReduceMachine Learning with SparkAutomationWhy Automated AI/ML?Limitations of AutoMLExisting Automated Machine Learning SolutionsSummary
Overview of CloudsConcerns about the CloudPublic and PrivateHybridMulticloudCloud ConstructionUsing AI on Hybrid CloudsPrivacy and SecurityPortability and ScalabilityProcessing and Computing PowerExample of AI on Hybrid CloudsPractical SolutionsThe Future of AI on Hybrid CloudsSummary
What Makes Enterprises Unique?Current Challenges, Trends, and OpportunitiesLittle DataInaccessible Data FormatsEnsuring Accountability and InterpretabilityFairness, Trust, and TransparencyScalabilitySocial ImplicationsSummary

Content preview from Getting Started with Artificial Intelligence, 2nd Edition

Chapter 6. Hybrid Clouds

Cloud is about how you do computing, not where you do computing.

Paul Maritz, CEO of VMware

By this point, you probably have a good understanding of the cloud (and cloud computing.) We tend to equate all the cloud-related technology we use in our daily lives to the public version—from Netflix to Gmail to Amazon, almost everything we do or deal with daily has public cloud roots. But we actually use more than just the public cloud. In previous chapters, most of the topics centered around using public APIs and public cloud computing to perform AI tasks. But what happens when that doesn’t fit an organization’s requirements? We’ll discuss numerous situations where utilizing only a single cloud type doesn’t make sense, and we need to look to hybrid and multicloud solutions, especially for AI.

Many readers will be surprised to learn how prevalent hybrid and multicloud are in the enterprise. According to a study by Flexera, 93% of enterprises have a multicloud strategy, and 87% a hybrid cloud strategy. Of these, they average using 2.2 public and 2.2 private clouds each. And Gartner data shows that 81% of public cloud users choose two or more providers. But while most enterprises are using the cloud, they’ve yet to embrace it fully. McKinsey estimates that less than 20% of enterprise workloads have moved to the cloud, presenting a tremendous opportunity. The numbers may vary slightly, but the direction is an increasing use of hybrid and multicloud environments ...