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 4. Computer Vision

Some people call this artificial intelligence, but the reality is this technology will enhance us. So instead of artificial intelligence, I think we’ll augment our intelligence.

Ginni Rometty, Executive Chairman of IBM

Take a moment and look up from this book. Examine the room around you and take a quick inventory of what you see. Perhaps a desk, some chairs, bookshelves, and maybe even your laptop. Identifying these items is an effortless process for a human, even a young child.

Speaking of children, it’s quite easy to teach them the difference between multiple objects. Over time, parents show them items or pictures and then repeat the name or description. Show them a picture of an apple, and then repeat the word apple. In the kitchen, hand them an apple, and then repeat the word apple. Eventually, through much repetition, the child learns what an apple is along with its many color and shape variations—red, green, yellow. Over time, we provide information as to what is a correct example and what isn’t. But how does this translate to machines? How can we train computers to recognize patterns visually, as the human brain does?

Training computer vision models is done in much the same way as teaching children about objects. Instead of a person being shown physical items and having them identified, however, the computer vision algorithms are provided many examples of images that have been tagged with their contents. In addition to these positive examples ...