DIY AI WITH AZURE
COGNITIVE SERVICES
PRIYANKA SHAH
AI42
Azure Cognitive services Basics
Agenda
Concepts and Types
How to : Tutorials
Demo
I AM…
• AI/IoT Offering Leadership @Avanade
• Microsoft AI MVP
• Data science and Big data solution engineer.
• Full stack developer.
• Passionate about new technologies, love to code, blog
/ talk about AI, ML.NET, Microsoft technology stack.
• Environment enthusiast
• Twitter: @fuzzymind1
AZURE COGNITIVE
SERVICES
• AI IS A NECESSITY , NOT A LUXURY ANYMORE!
WHAT ARE AZURE COGNITIVE
SERVICES?
bring AI within reach of
every developer—
without requiring
machine-learning
expertise.
Vision, Speech,
Language, Web
Search, and
Decision..
create
applications that
can see, hear,
speak,
understand, and
even begin to
reason..
Cognitive Services are
APIs, SDKs, and services
available to help
developers build
intelligent applications.
Types of Cognitive Services
 Anomaly Detector
 Personalizer
 Content Moderator
DECISION
 Bing Auto Suggest
 Bing Custom Search
 Bing Entity Search
 Bing News Search
 Bing Image Search
 Bing Spell check
 Bing Video search
 Bing Visual search
 Bing Web search
WEB SEARCH
 Immersive reader
 Language Understanding
 Text Analytics.
 Q and A maker
 Text Translator
LANGUAGE
 Speech to Text
 Text to Speech
 Speaker Recognition
 Speech Translation.
SPEECH
 Computer Vision
 Custom Vision
 Face recognition
 Ink / Form recognizer
 Video Indexer
VISION
Usage…
 Need to choose the
algorithm and need to
train on very specific
data.
 Can use a generalized
solution.
 Access solution from a
programming REST API
or SDK.
.
Use Machine
Learning when…
Use Cognitive
services when…
VISION APIs
SPEECH APIs
LANGUAGE APIs
DECISION APIs
Features of Cognitive services
$
$
Just Get your Azure
subscription!!!
And get, set, go…
Q&A

AI42_DIY_Cognitiveservices.pptx

  • 1.
    DIY AI WITHAZURE COGNITIVE SERVICES PRIYANKA SHAH AI42
  • 2.
    Azure Cognitive servicesBasics Agenda Concepts and Types How to : Tutorials Demo
  • 3.
    I AM… • AI/IoTOffering Leadership @Avanade • Microsoft AI MVP • Data science and Big data solution engineer. • Full stack developer. • Passionate about new technologies, love to code, blog / talk about AI, ML.NET, Microsoft technology stack. • Environment enthusiast • Twitter: @fuzzymind1
  • 4.
    AZURE COGNITIVE SERVICES • AIIS A NECESSITY , NOT A LUXURY ANYMORE!
  • 5.
    WHAT ARE AZURECOGNITIVE SERVICES? bring AI within reach of every developer— without requiring machine-learning expertise. Vision, Speech, Language, Web Search, and Decision.. create applications that can see, hear, speak, understand, and even begin to reason.. Cognitive Services are APIs, SDKs, and services available to help developers build intelligent applications.
  • 6.
    Types of CognitiveServices  Anomaly Detector  Personalizer  Content Moderator DECISION  Bing Auto Suggest  Bing Custom Search  Bing Entity Search  Bing News Search  Bing Image Search  Bing Spell check  Bing Video search  Bing Visual search  Bing Web search WEB SEARCH  Immersive reader  Language Understanding  Text Analytics.  Q and A maker  Text Translator LANGUAGE  Speech to Text  Text to Speech  Speaker Recognition  Speech Translation. SPEECH  Computer Vision  Custom Vision  Face recognition  Ink / Form recognizer  Video Indexer VISION
  • 7.
    Usage…  Need tochoose the algorithm and need to train on very specific data.  Can use a generalized solution.  Access solution from a programming REST API or SDK. . Use Machine Learning when… Use Cognitive services when…
  • 8.
  • 9.
  • 10.
  • 11.
  • 12.
  • 14.
    Just Get yourAzure subscription!!! And get, set, go…
  • 15.

Editor's Notes

  • #3 Here the plan of journey. We will start by the beginning by understanding what serverless. Then We will talk about Azure Logic App and Flow. We will then spend sometimes and I will show you a few demos with Azure Functions And we will finish by an example of how all those services can work all together.
  • #4 Logic apps are great at connecting resources across the cloud, but they are also capable of integrating with on-premises resources with the on-premises data gateway. That means you can, for example, kick off a workflow in the cloud that results in the execution of a store procedure on your SQL database tucked away in your corporate data center.
  • #13 With serverless, the server, including hardware, infrastructure and configuration of the operating system are all abstracted away. You don’t even have to worry about a web service because it’s provided as part of the platform. Serverless compute is a fully managed service. Some refer to it as Functions as a Service OS and Framework patching is performed for you There is zero administrative tasks and no need to manage any infrastructure You just deploy your code (function) and it runs Your code runs within seconds and for typically shorter periods of times (minutes vs. hours or days) Serverless compute scales quickly (almost instantly) and vastly Automatically scales within seconds No scale configuration is required (there is no way to configure scale or limits) Scales to match any given workload. Scales from zero to handle tens of thousands concurrent functions invocations within seconds Pay only for the time your code is running Serverless compute reacts to events React, in near real-time, to events and triggers Triggered by virtually any event from both inside and outside of Azure A key differentiator about serverless is micro-billing. Serverless resources are billed only when used. That means that you aren’t paying to anticipate an increase in workload, but only when the workload hits. Serverless scales with your business. Let’s take a closer look at micro-billing.
  • #14 Microsoft Tech Summit FY17