Upgrade to Pro — share decks privately, control downloads, hide ads and more …

How to Build an AI-driven serverless applicatio...

How to Build an AI-driven serverless application without any AI experience

A practical example of using serverless functions for app development. How to build an AI-driven application without knowing anything about AI, but using a lot of serverless offerings. Once done, the app will be able to detect words, lines and their respective positions in images using Amazon Rekognition and convert them into speech using Amazon Polly

Zamira Jaupaj

November 07, 2019
Tweet

More Decks by Zamira Jaupaj

Other Decks in Technology

Transcript

  1. @zamirajaupaj Are you concerned about the increase artificial intelligence? No,

    but i’m concerned about the decrease in real intelligence First Day
  2. @zamirajaupaj AI vs Machine Learning vs Deep Learning Artificial Intelligence

    Machine Learning Deep Learning Algorithms that enable self learning to mimic human intelligence Statistical techniques that learn from a series input Computers system that perform tasks that would usually require human intelligence
  3. @zamirajaupaj Go to the new Destination Input City Type Beautiful

    Avenue Art & History Type of Trip With Who Food and Wine Travel Time Christmas Light Luxury Hotel Luxury Car Airplane Visit Museum Output Romantic Old City Winter Paris Budget
  4. @zamirajaupaj Human vs machine Human Abilities Artificial intelligence Results Seeing

    Computer Vision, Image Recognition Handwriting recognition Cancer detection Communication Natural Language Understanding Spam Detection, Translation, Voice Creating Computational creativity Self Driving Cars Learning Machine Learning, Deep Learning All of the Above
  5. @zamirajaupaj Amazon Polly Convert text to lifelike speech. Synthesize speech

    that sounds like the human voice. Low latency responses allow developers to build real time system. With up to 3000 characters you can listen, download, or save immediately. For up to 100,000 characters, your task must be saved to an S3 bucket. Amazon Polly
  6. @zamirajaupaj Amazon Polly Mobile Application Education eLearning Internet of things

    Games Content Creation Call Center Fitness band Custom lexicon to tell the pronunciation Amazon Polly
  7. @zamirajaupaj Amazon Rekognition Image Analysis Rekognition software on the top

    of deep learning Recommended best Photo Improve online dating match recommendation Personalize advising
  8. @zamirajaupaj Amazon Comprehend Amazon Comprehend recognizes entities, extracts key phrases,

    detects language, and analyzes sentiment. Analyze your text, type or paste it in the text box
  9. @zamirajaupaj Steve Jobs (February 24, 1955 – October 5, 2011)

    was an American business magnate and investor. He was the chairman, chief executive officer (CEO), and co-founder of Apple Inc. Amazon Comprehend Entity: Steve Jobs -> Person February 24, 1955 October 5, 2011 -> date Apple Inc -> Organization Key phrases: CEO , Chairman, Co-Founder Language: English Sentiment: Natural
  10. @zamirajaupaj Amazon Lex Amazon Lex is a service for building

    conversational interfaces using voice and text. With Lex, the same deep learning engine that powers Alexa. Enabling you to bring sophisticated, natural language chatbots to your new and existing applications
  11. @zamirajaupaj Transform text to audio Mobile Amazon Polly Amazon Rekognition

    Lambda function Amazon DynamoDB S3 Bucket Amazon Cognito ME