Microsoft Cognitive Services
Presented by Ali zoljodi
1

Topics
• What is the Microsoft Cognitive Services?
• Why Microsoft Cognitive Services?
• Cognitive Services API Collection
• Vision
• Text Analytics API
• Microsoft Translator Text API
• Language
• Microsoft Cognitive vs. Google Tensorflow
• Companies using Microsoft cognitive services
• Resources
2

What is the Microsoft Cognitive Services?
• Set of APIs , SDKs and Services for Making more intelligent
applications.
• MS Cognitive enable developers to add this abilities to their
applications:
 Emotion and video detection
 Facial , speech and vision recognition
 Speech and language understanding
• You can use this service as an Azure service or run it as a local
framework
• MS Cognitive is an open source project
3

Why Microsoft Cognitive Services?
• Easy
 Use REST API
 Just a few lines of code required
• Flexible
 Make the same API code call on iOS , Android and Windows
 Integrate into the language and platform of your choice
• Tested
 Built by experts in their field from Microsoft Research , Bing and Azure
Machine Learning
• Quality documentation , sample code and community support
4

Cognitive Services API Collection
• Vision
Computer vision | Emotion | Face | Video
• Speech
Bing Speech | Custom Recognition | Speaker Recognition
• Language
Bing Spell Check | Language Understanding | Linguistic Analysis | Text Analytics |
Translator | Web Language Model
• Knowledge
Academic Knowledge | Entity linking I Knowledge Exploration | Recommendations
• Search
Bing Autosuggest | Bing Image search | Bing News Search | Bing Video Search | Bing
Web Search
5

Vision
• Computer Vision API
Distill actionable information from images
• Face API
Detect , identify , analyze , organize and tag faces in photos
• Emotion API
Personalize experiences with emotion recognition
• Video API
Analyze , edit and process videos within your app
6

Language
• Text Analytics API
Detect sentiment , key phrase , topics and language from your text
• Language Understanding Intelligent Service
Teach your apps to understand commands from your users
• Bing Spell Check API
Detect and correct spelling mistakes within your app
• Web language Model API
Leverage the power of language models trained on web-scale data
• Linguistic Analysis API
Easily parse complex text with language analysis
7

Text Analytics API
• Detect sentiment , key phrases , topics and language
 Sentiment – Is text positive or negative?
 Key phrases – What are people discussing in a single articles?
 Topics – What are people discussing across many articles?
 Languages – What language is text written in?
• Supported languages:
 Sentiment: en (English) , es (Spanish) , fr (French) , pt (Portuguese)
 Key phrases : en (English) , es (Spanish) , de (German) , ja (Japanese)
8

Language Understanding Intelligent Service
• LUIS model includes:
• Intents
• Entities
• Example utterances
9

Language Understanding Intelligent Service
• Methods that LUIS provides to improve prediction accuracy:
• Active learning
• Phrase lists
• Patterns
10

Microsoft Translator Text API
• Set of open web APIs that can be integrated into any website or app,
on any device ad operating systems
• Support 50+ languages for text translation
• Easy to get started
• Sign-in to Azure DataMarket with Microsoft Account
• Free Tier: Up to 2 million characters per month
• Subscribe to Microsoft Translator API
• Register your app and create App ID & Secret
11

Microsoft Cognitive vs. Google Tensorflow
Microsoft Cognitive
• Much faster
• Better API design
• Scalability
Google TensorFlow
• Better community support
• Mobile deep learning tools
• Free cloud computing service
12

Companies using Microsoft cognitive services
• Uber
• GrayMeta
• Cloudinary
• Dixons Carphone
• Blucup
• pivothead
13

Resources
• mspoweruser.com/microsoft-8-reasons-why-you-should-switch-from-
tensorflow-to-cntk/
• azure.microsoft.com/en-us/services/cognitive-services/
• www.microsoft.com/en-us/translator/translatorapi.aspx
• azure.microsoft.com/en-us/services/cognitive-services/
14