SlideShare a Scribd company logo
1 of 49
Download to read offline
Python으로
IoT(Internet of Things),
Cognitive, Machine Learning
3종 셋트 활용하기
김영욱 Evangelist
Microsoft / DX / 부장
youngwook@outlook.com
War of IT
https://github.com/KoreaEva/Python.git
Microsoft	
  
LOVE	
  ♥
Microsoft ♥ Open Source
PTVS(Python	
  Tools	
  for	
  Visual	
  Studio)
NTVS(Node.js	
  Tools	
  for	
  Visual	
  Studio)
RTVS(R	
  Tools	
  for	
  Visual	
  Studio)
PHP	
  Tools	
  for	
  Visual	
  Studio
Visual	
  C++	
  for	
  Linux
Microsoft is Open Source
Microsoft ♥ Python
Sensors on
Linux (Rasberian)
SQL Database Machine Learning
Power BIStream Analytics
IoT Hubs
Blob / Table
Cognitive
Services
Microsoft Cognitive Services
IoT Service
Machine Learning
Visual Studio Code
http://visualstudio.com
Cognitive Service
http://www.Microsoft.com/cognitive
Microsoft 

Cognitive 

Services
Give your apps 

a human side
Vision
From faces to feelings, allow your 

apps to understand images and video
Speech
Hear and speak to your users by filtering noise,
identifying speakers, and understanding intent
Language
Process text and learn how to
recognize what users want
Knowledge
Tap into rich knowledge amassed from 

the web, academia, or your own data
Search
Access billions of web pages, images, videos,
and news with the power of Bing APIs
Cognitive Services
Apps Powered by MS Cognitive Services
ProjectMurphy.n
et
CaptionBot.ai
I think it’s a person sitting in front of a
computer and he seems ☺. I am 99%
sure that’s Bill Gates
Celebslike.me
Roll your own with REST APIs
Simple to add: just a few lines 

of code required
Make the same API code call on
iOS, Android, and Windows
Integrate into the language 

and platform of your choice
Built by experts in their field from
Microsoft Research, Bing, and Azure
Machine Learning
Quality documentation, sample
code, and community support
Easy Flexible Tested
GET A

KEY
BUILD
Why Microsoft 

Cognitive Services ?
Cognitive Services
Emotion
Speaker
Recognition
Speech
Custom RecognitionComputer Vision
Face
Video
microsoft.com/cognitive
SearchSpeech Language KnowledgeVision
Linguistic Analysis
Language
Understanding
Bing Spell Check
Entity Linking
Knowledge
Exploration
Academic
Knowledge
Bing
Image Search
Bing
Video Search
Bing
Web Search
WebLM
Text Analytics Recommendations
Bing
Autosuggest
Bing
News Search
Translator
Cognitive Services
Emotion
Speaker
Recognition
Speech
Custom RecognitionComputer Vision
Face
Video
SearchSpeech Language KnowledgeVision
Linguistic Analysis
Language
Understanding
Bing Spell Check
Entity Linking
Knowledge
Exploration
Academic
Knowledge
Bing
Image Search
Bing
Video Search
Bing
Web Search
WebLM
Text Analytics Recommendations
Bing
Autosuggest
Bing
News Search
Translator
microsoft.com/cognitive
{Subscription Key}

JSON
• http://www.json.org/json-ko.html
Vision API

Computer Vision

Emotion

Face
Demo
Language

Bing Spell check

Language Understanding

Linguistic Analysis

Text Analytics 

WebLM
Demo
Bing

Bing Web Search

Bing Image Search

Bing Video Search

Bing News Search

Bing Autosuggest
Bing beyond search in bing.comSmarter, more
engaging
experiences
Trusted by industry-
leading experiences
Introducing Bing Search API v5
Web Search
Image Search
Video Search
News Search
Autosuggest
Spell Check
Search API v5
REST
Enhanced Search and Filtering Capabilities
Ongoing Improvements and Support
Web-
Scale
High
Performance
Secure
(HTTPs)
Web Search APIWeb Search API
*screenshots show actual search results on bing.com
https://bingapis.azure-api.net/v5/search?
q=nasa
Get relevant web and answer results and metadata with one API
call
{
“_type”: “SearchResponse”,
“queryContent”: {…},
“webPages”: {…},
“news”: {…},
“images”: {…},
“videos”: {…},
“relatedSearches”: {…},
“rankingResponse”: {…}
}
{
“answerType”:”WebPages”,
“resultIndex”:0,…
},
{
“answerType”:”News”,
“resultIndex”:1,…
}
Ranking Response
Search Response
Web
Results
Deep
Links
(1st Algo)
News
Results
Image
Results
Video
Results
Related
Searches
Vertical Search APIs
https://bingapis.azure-api.net/v5/images/search?q=shuttle
+launch
• Enhanced metadata and filters (size, license, style, freshness, color)
• Image insights (entity recognition, visually similar)
Image Search API
source: nasa.gov
https://bingapis.azure-api.net/v5/videos/search?q=viral+videos
• Enhanced metadata and filters (price, resolution, length,
freshness)
• Motion thumbnails (video preview)
https://bingapis.azure-api.net/v5/news/search?q=cuba
• News by category/market, and trending news
• Rich article metadata (featured entities)
source: youtube.com
Video Search API
*screenshots show actual search results in bing.com
Get more results, features and metadata tailored to each search
vertical
News Search API
source: cnn.com
Demo
• Sign up and get started today for free at
www.microsoft.com/cognitive
Developer Call to Action
Internet of Things
http://www.microsoft.com/iot
Sensors on
Linux (Rasberian)
SQL Database Machine Learning
Power BIStream Analytics
IoT Hubs
Blob / Table
Cognitive
Services
Microsoft Cognitive Services
IoT Service
Machine Learning
• 지원되는 프로토콜은 HTTP1.1, MQTT, AMQP 1.0 (16년 4월 OPC 공식지원 발표)
• LWM2M, CoAP 등의 지원은 계획 중이나 시기 미정
IoT Hub
Stream Analysis
Sensors on
Linux (Rasberian)
SQL Database Machine Learning
Power BIStream Analytics
IoT Hubs
Blob / Table
Cognitive
Services
Microsoft Cognitive Services
IoT Service
Machine Learning
Machine Learning
http://www.microsoft.com/iot
Microsoft & Machine Learning

15 years of realizing innovation
SQL Server
enables 

data mining
Computers
work on
users behalf,
filtering junk
email
Microsoft
Kinect can
watch users
gestures
Microsoft
launches 

Azure
Machine
Learning
Microsoft
search engine
built with
machine
learning
Bing Maps
ships with ML
traffic-
prediction
service
Successful,
real-time,
speech-to-
speech
translation
John Platt, 

Distinguished scientist at
Microsoft Research
1999 201220082004 201420102005
Machine learning is pervasive throughout 

Microsoft products.“ ”
One solution for Machine Learning - from data to results
Azure Portal
Azure Ops
Team
ML Studio
Data Scientist
HDInsight
Azure Storage
Desktop Data
Azure Portal & 

ML API service
Azure Ops
Team
PowerBI/
Dashboards
Mobile AppsWeb Apps
ML API service Developer
Machine Learning
Data I/O
Taking Data & preparing for
Analysis
Dimensionality reduction. E.g. Kinect measures 1000 points, 6 are
relevant
Fitting Model selection; calibration; assessment
R – free scripts/graphics, many packages based on Vector Data.
Metrics to allow us to describe the data. E.g. Mean, Correlation…
Tools used for Text Input. E.g. ‘What is the theme of this essay?’
Here are the main steps in a typical machine learning workflow:1. Data Collection: Collecting and preparing the raw data you'll use to train your model. This may involve cleaning, formatting, feature engineering, etc. 2. Data Exploration: Exploring your data to understand its characteristics and identify any issues. This involves calculating statistics, visualizing relationships, and checking for biases.3. Model Selection: Choosing the machine learning model that is best suited for your problem - supervised vs unsupervised, regression vs classification, etc. 4. Feature Engineering: Transforming raw data into "features" the learning algorithm can use. This may involve discretization, normalization, principal component analysis, etc.5

More Related Content

What's hot

Microsoft Botframework and LUIS
Microsoft Botframework and LUISMicrosoft Botframework and LUIS
Microsoft Botframework and LUISIan Philpot
 
Building an IoT Massive Multiplayer Game in 60 Minutes - TechBash 2017
Building an IoT Massive Multiplayer Game in 60 Minutes - TechBash 2017Building an IoT Massive Multiplayer Game in 60 Minutes - TechBash 2017
Building an IoT Massive Multiplayer Game in 60 Minutes - TechBash 2017Eran Stiller
 
Bot-Tender: A Chat Bot Walks into a Bar - TechBash 2017
Bot-Tender: A Chat Bot Walks into a Bar - TechBash 2017Bot-Tender: A Chat Bot Walks into a Bar - TechBash 2017
Bot-Tender: A Chat Bot Walks into a Bar - TechBash 2017Eran Stiller
 
Python For Data Science
Python For Data SciencePython For Data Science
Python For Data ScienceAlvin Sim
 
virtual-2021-data.sql_.saturday.la-Building database interactions with users ...
virtual-2021-data.sql_.saturday.la-Building database interactions with users ...virtual-2021-data.sql_.saturday.la-Building database interactions with users ...
virtual-2021-data.sql_.saturday.la-Building database interactions with users ...Luis Beltran
 
Designing XR Experiences with Speech & Natural Language Understanding in Unity
Designing XR Experiences with Speech & Natural Language Understanding in UnityDesigning XR Experiences with Speech & Natural Language Understanding in Unity
Designing XR Experiences with Speech & Natural Language Understanding in UnityUnity Technologies
 
Introduction of Dialogflow with google assistant and Artificial intelligence
Introduction of Dialogflow with google assistant and Artificial intelligenceIntroduction of Dialogflow with google assistant and Artificial intelligence
Introduction of Dialogflow with google assistant and Artificial intelligenceHarshil Barot
 

What's hot (8)

Microsoft Botframework and LUIS
Microsoft Botframework and LUISMicrosoft Botframework and LUIS
Microsoft Botframework and LUIS
 
Mobile stategy
Mobile stategyMobile stategy
Mobile stategy
 
Building an IoT Massive Multiplayer Game in 60 Minutes - TechBash 2017
Building an IoT Massive Multiplayer Game in 60 Minutes - TechBash 2017Building an IoT Massive Multiplayer Game in 60 Minutes - TechBash 2017
Building an IoT Massive Multiplayer Game in 60 Minutes - TechBash 2017
 
Bot-Tender: A Chat Bot Walks into a Bar - TechBash 2017
Bot-Tender: A Chat Bot Walks into a Bar - TechBash 2017Bot-Tender: A Chat Bot Walks into a Bar - TechBash 2017
Bot-Tender: A Chat Bot Walks into a Bar - TechBash 2017
 
Python For Data Science
Python For Data SciencePython For Data Science
Python For Data Science
 
virtual-2021-data.sql_.saturday.la-Building database interactions with users ...
virtual-2021-data.sql_.saturday.la-Building database interactions with users ...virtual-2021-data.sql_.saturday.la-Building database interactions with users ...
virtual-2021-data.sql_.saturday.la-Building database interactions with users ...
 
Designing XR Experiences with Speech & Natural Language Understanding in Unity
Designing XR Experiences with Speech & Natural Language Understanding in UnityDesigning XR Experiences with Speech & Natural Language Understanding in Unity
Designing XR Experiences with Speech & Natural Language Understanding in Unity
 
Introduction of Dialogflow with google assistant and Artificial intelligence
Introduction of Dialogflow with google assistant and Artificial intelligenceIntroduction of Dialogflow with google assistant and Artificial intelligence
Introduction of Dialogflow with google assistant and Artificial intelligence
 

Viewers also liked

파이썬 데이터 분석 3종세트
파이썬 데이터 분석 3종세트파이썬 데이터 분석 3종세트
파이썬 데이터 분석 3종세트itproman35
 
공개SW와 개발방법론(오픈소스 성공요인 사례)
공개SW와 개발방법론(오픈소스 성공요인 사례)공개SW와 개발방법론(오픈소스 성공요인 사례)
공개SW와 개발방법론(오픈소스 성공요인 사례)mosaicnet
 
2016_ClinicalSchoolsWithPlymouthUniversity_LATOUR
2016_ClinicalSchoolsWithPlymouthUniversity_LATOUR2016_ClinicalSchoolsWithPlymouthUniversity_LATOUR
2016_ClinicalSchoolsWithPlymouthUniversity_LATOURChrist Dean
 
Flour Mills Management System
Flour Mills Management SystemFlour Mills Management System
Flour Mills Management Systemsaleem awan
 
vsource - Smarter Talent Acquisition
vsource - Smarter Talent Acquisitionvsource - Smarter Talent Acquisition
vsource - Smarter Talent AcquisitionTam Dinh
 
School Management System
School Management SystemSchool Management System
School Management Systemsaleem awan
 
Colegio técnico profesional de carrizal
Colegio técnico profesional de carrizalColegio técnico profesional de carrizal
Colegio técnico profesional de carrizalMarkus Agnus
 
Ação: Casa dos Idosos de Sta Etelvina
Ação: Casa dos Idosos de Sta EtelvinaAção: Casa dos Idosos de Sta Etelvina
Ação: Casa dos Idosos de Sta EtelvinaSamara Castro
 

Viewers also liked (20)

파이썬 데이터 분석 3종세트
파이썬 데이터 분석 3종세트파이썬 데이터 분석 3종세트
파이썬 데이터 분석 3종세트
 
공개SW와 개발방법론(오픈소스 성공요인 사례)
공개SW와 개발방법론(오픈소스 성공요인 사례)공개SW와 개발방법론(오픈소스 성공요인 사례)
공개SW와 개발방법론(오픈소스 성공요인 사례)
 
The Digital Divide
The Digital DivideThe Digital Divide
The Digital Divide
 
2016_ClinicalSchoolsWithPlymouthUniversity_LATOUR
2016_ClinicalSchoolsWithPlymouthUniversity_LATOUR2016_ClinicalSchoolsWithPlymouthUniversity_LATOUR
2016_ClinicalSchoolsWithPlymouthUniversity_LATOUR
 
Flour Mills Management System
Flour Mills Management SystemFlour Mills Management System
Flour Mills Management System
 
Alejandra Valarezo
Alejandra ValarezoAlejandra Valarezo
Alejandra Valarezo
 
FarmerGameScreenshots
FarmerGameScreenshotsFarmerGameScreenshots
FarmerGameScreenshots
 
vsource - Smarter Talent Acquisition
vsource - Smarter Talent Acquisitionvsource - Smarter Talent Acquisition
vsource - Smarter Talent Acquisition
 
School Management System
School Management SystemSchool Management System
School Management System
 
HISTORIA DEL TELEFONO
HISTORIA DEL TELEFONO HISTORIA DEL TELEFONO
HISTORIA DEL TELEFONO
 
RMG IN BANGLADESH
RMG IN BANGLADESHRMG IN BANGLADESH
RMG IN BANGLADESH
 
Ramon llull
Ramon llullRamon llull
Ramon llull
 
Colegio técnico profesional de carrizal
Colegio técnico profesional de carrizalColegio técnico profesional de carrizal
Colegio técnico profesional de carrizal
 
Power vane
Power vanePower vane
Power vane
 
Deb OBrien Awards
Deb OBrien AwardsDeb OBrien Awards
Deb OBrien Awards
 
Digital presence
Digital presenceDigital presence
Digital presence
 
Historia del telefono
Historia del telefonoHistoria del telefono
Historia del telefono
 
Exp 1
Exp 1Exp 1
Exp 1
 
Proyecto
ProyectoProyecto
Proyecto
 
Ação: Casa dos Idosos de Sta Etelvina
Ação: Casa dos Idosos de Sta EtelvinaAção: Casa dos Idosos de Sta Etelvina
Ação: Casa dos Idosos de Sta Etelvina
 

Similar to Here are the main steps in a typical machine learning workflow:1. Data Collection: Collecting and preparing the raw data you'll use to train your model. This may involve cleaning, formatting, feature engineering, etc. 2. Data Exploration: Exploring your data to understand its characteristics and identify any issues. This involves calculating statistics, visualizing relationships, and checking for biases.3. Model Selection: Choosing the machine learning model that is best suited for your problem - supervised vs unsupervised, regression vs classification, etc. 4. Feature Engineering: Transforming raw data into "features" the learning algorithm can use. This may involve discretization, normalization, principal component analysis, etc.5

Tech talk - Microsoft A.I.
Tech talk - Microsoft A.I.Tech talk - Microsoft A.I.
Tech talk - Microsoft A.I.Cheah Eng Soon
 
Human vs Bot: Giocare a Sasso-Carta-Forbici - Matteo Valoriani, Antimo Musone...
Human vs Bot: Giocare a Sasso-Carta-Forbici - Matteo Valoriani, Antimo Musone...Human vs Bot: Giocare a Sasso-Carta-Forbici - Matteo Valoriani, Antimo Musone...
Human vs Bot: Giocare a Sasso-Carta-Forbici - Matteo Valoriani, Antimo Musone...Codemotion
 
Building the intelligent future
Building the intelligent futureBuilding the intelligent future
Building the intelligent futureMoscow Digital
 
Da 0 all'AI conversazionale usando Microsoft Azure
Da 0 all'AI conversazionale usando Microsoft AzureDa 0 all'AI conversazionale usando Microsoft Azure
Da 0 all'AI conversazionale usando Microsoft AzureMarco Parenzan
 
.NET Fest 2018. Олександр Краковецький. Microsoft AI: створюємо програмні ріш...
.NET Fest 2018. Олександр Краковецький. Microsoft AI: створюємо програмні ріш....NET Fest 2018. Олександр Краковецький. Microsoft AI: створюємо програмні ріш...
.NET Fest 2018. Олександр Краковецький. Microsoft AI: створюємо програмні ріш...NETFest
 
Solvion Trendwerkstatt - Microsoft Azure + Bots
Solvion Trendwerkstatt - Microsoft Azure + BotsSolvion Trendwerkstatt - Microsoft Azure + Bots
Solvion Trendwerkstatt - Microsoft Azure + BotsHolzerKerstin
 
PDCConf2021 - Serverless WhatsApp Chatbot with Azure AI.pptx
PDCConf2021 - Serverless WhatsApp Chatbot with Azure AI.pptxPDCConf2021 - Serverless WhatsApp Chatbot with Azure AI.pptx
PDCConf2021 - Serverless WhatsApp Chatbot with Azure AI.pptxLuis Beltran
 
DevOpsSummit 2017 - Azure Cognitive Services
DevOpsSummit 2017 - Azure Cognitive ServicesDevOpsSummit 2017 - Azure Cognitive Services
DevOpsSummit 2017 - Azure Cognitive ServicesVitor Meriat
 
Cortana intelligence suite for projects & hacks
Cortana intelligence suite for projects & hacksCortana intelligence suite for projects & hacks
Cortana intelligence suite for projects & hacksLee Stott
 
Azure Global Bootcamp 2017 - Microsoft Cognitive Services
Azure Global Bootcamp 2017 - Microsoft Cognitive ServicesAzure Global Bootcamp 2017 - Microsoft Cognitive Services
Azure Global Bootcamp 2017 - Microsoft Cognitive ServicesGeorge Spyrou
 
infoShare AI Roadshow 2018 - Dorian Nikoniuk (Microsoft) - Usługi poznawcze, ...
infoShare AI Roadshow 2018 - Dorian Nikoniuk (Microsoft) - Usługi poznawcze, ...infoShare AI Roadshow 2018 - Dorian Nikoniuk (Microsoft) - Usługi poznawcze, ...
infoShare AI Roadshow 2018 - Dorian Nikoniuk (Microsoft) - Usługi poznawcze, ...Infoshare
 
Tour de France Azure PaaS 6/7 Ajouter de l'intelligence
Tour de France Azure PaaS 6/7 Ajouter de l'intelligenceTour de France Azure PaaS 6/7 Ajouter de l'intelligence
Tour de France Azure PaaS 6/7 Ajouter de l'intelligenceAlex Danvy
 
Ai big dataconference_krakovetskyi_microsoft ai a new era of smart solutions
Ai big dataconference_krakovetskyi_microsoft ai a new era of smart solutionsAi big dataconference_krakovetskyi_microsoft ai a new era of smart solutions
Ai big dataconference_krakovetskyi_microsoft ai a new era of smart solutionsOlga Zinkevych
 
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)Naoki (Neo) SATO
 
Making Apps More Human - Intro to Microsoft Cognitive Services
Making Apps More Human - Intro to Microsoft Cognitive ServicesMaking Apps More Human - Intro to Microsoft Cognitive Services
Making Apps More Human - Intro to Microsoft Cognitive ServicesMatthew Soucoup
 

Similar to Here are the main steps in a typical machine learning workflow:1. Data Collection: Collecting and preparing the raw data you'll use to train your model. This may involve cleaning, formatting, feature engineering, etc. 2. Data Exploration: Exploring your data to understand its characteristics and identify any issues. This involves calculating statistics, visualizing relationships, and checking for biases.3. Model Selection: Choosing the machine learning model that is best suited for your problem - supervised vs unsupervised, regression vs classification, etc. 4. Feature Engineering: Transforming raw data into "features" the learning algorithm can use. This may involve discretization, normalization, principal component analysis, etc.5 (20)

Tech talk - Microsoft A.I.
Tech talk - Microsoft A.I.Tech talk - Microsoft A.I.
Tech talk - Microsoft A.I.
 
Intelligent ChatBot
Intelligent ChatBotIntelligent ChatBot
Intelligent ChatBot
 
AI Machine vs Human
AI Machine vs HumanAI Machine vs Human
AI Machine vs Human
 
Human vs Bot: Giocare a Sasso-Carta-Forbici - Matteo Valoriani, Antimo Musone...
Human vs Bot: Giocare a Sasso-Carta-Forbici - Matteo Valoriani, Antimo Musone...Human vs Bot: Giocare a Sasso-Carta-Forbici - Matteo Valoriani, Antimo Musone...
Human vs Bot: Giocare a Sasso-Carta-Forbici - Matteo Valoriani, Antimo Musone...
 
Building the intelligent future
Building the intelligent futureBuilding the intelligent future
Building the intelligent future
 
Da 0 all'AI conversazionale usando Microsoft Azure
Da 0 all'AI conversazionale usando Microsoft AzureDa 0 all'AI conversazionale usando Microsoft Azure
Da 0 all'AI conversazionale usando Microsoft Azure
 
.NET Fest 2018. Олександр Краковецький. Microsoft AI: створюємо програмні ріш...
.NET Fest 2018. Олександр Краковецький. Microsoft AI: створюємо програмні ріш....NET Fest 2018. Олександр Краковецький. Microsoft AI: створюємо програмні ріш...
.NET Fest 2018. Олександр Краковецький. Microsoft AI: створюємо програмні ріш...
 
Cognitive Services
Cognitive ServicesCognitive Services
Cognitive Services
 
Microsoft Cognitive Service, Tap into the Power of Machine Learning with Easy...
Microsoft Cognitive Service, Tap into the Power of Machine Learning with Easy...Microsoft Cognitive Service, Tap into the Power of Machine Learning with Easy...
Microsoft Cognitive Service, Tap into the Power of Machine Learning with Easy...
 
Solvion Trendwerkstatt - Microsoft Azure + Bots
Solvion Trendwerkstatt - Microsoft Azure + BotsSolvion Trendwerkstatt - Microsoft Azure + Bots
Solvion Trendwerkstatt - Microsoft Azure + Bots
 
PDCConf2021 - Serverless WhatsApp Chatbot with Azure AI.pptx
PDCConf2021 - Serverless WhatsApp Chatbot with Azure AI.pptxPDCConf2021 - Serverless WhatsApp Chatbot with Azure AI.pptx
PDCConf2021 - Serverless WhatsApp Chatbot with Azure AI.pptx
 
Bots & Teams: el poder de Grayskull
Bots & Teams: el poder de GrayskullBots & Teams: el poder de Grayskull
Bots & Teams: el poder de Grayskull
 
DevOpsSummit 2017 - Azure Cognitive Services
DevOpsSummit 2017 - Azure Cognitive ServicesDevOpsSummit 2017 - Azure Cognitive Services
DevOpsSummit 2017 - Azure Cognitive Services
 
Cortana intelligence suite for projects & hacks
Cortana intelligence suite for projects & hacksCortana intelligence suite for projects & hacks
Cortana intelligence suite for projects & hacks
 
Azure Global Bootcamp 2017 - Microsoft Cognitive Services
Azure Global Bootcamp 2017 - Microsoft Cognitive ServicesAzure Global Bootcamp 2017 - Microsoft Cognitive Services
Azure Global Bootcamp 2017 - Microsoft Cognitive Services
 
infoShare AI Roadshow 2018 - Dorian Nikoniuk (Microsoft) - Usługi poznawcze, ...
infoShare AI Roadshow 2018 - Dorian Nikoniuk (Microsoft) - Usługi poznawcze, ...infoShare AI Roadshow 2018 - Dorian Nikoniuk (Microsoft) - Usługi poznawcze, ...
infoShare AI Roadshow 2018 - Dorian Nikoniuk (Microsoft) - Usługi poznawcze, ...
 
Tour de France Azure PaaS 6/7 Ajouter de l'intelligence
Tour de France Azure PaaS 6/7 Ajouter de l'intelligenceTour de France Azure PaaS 6/7 Ajouter de l'intelligence
Tour de France Azure PaaS 6/7 Ajouter de l'intelligence
 
Ai big dataconference_krakovetskyi_microsoft ai a new era of smart solutions
Ai big dataconference_krakovetskyi_microsoft ai a new era of smart solutionsAi big dataconference_krakovetskyi_microsoft ai a new era of smart solutions
Ai big dataconference_krakovetskyi_microsoft ai a new era of smart solutions
 
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
Microsoft + OpenAI: Recent Updates (Machine Learning 15minutes! Broadcast #74)
 
Making Apps More Human - Intro to Microsoft Cognitive Services
Making Apps More Human - Intro to Microsoft Cognitive ServicesMaking Apps More Human - Intro to Microsoft Cognitive Services
Making Apps More Human - Intro to Microsoft Cognitive Services
 

Recently uploaded

Vip Hot Call Girls 🫤 Mahipalpur ➡️ 9711199171 ➡️ Delhi 🫦 Whatsapp Number
Vip Hot Call Girls 🫤 Mahipalpur ➡️ 9711199171 ➡️ Delhi 🫦 Whatsapp NumberVip Hot Call Girls 🫤 Mahipalpur ➡️ 9711199171 ➡️ Delhi 🫦 Whatsapp Number
Vip Hot Call Girls 🫤 Mahipalpur ➡️ 9711199171 ➡️ Delhi 🫦 Whatsapp Numberkumarajju5765
 
Russian Call Girls Delhi Indirapuram {9711199171} Aarvi Gupta ✌️Independent ...
Russian  Call Girls Delhi Indirapuram {9711199171} Aarvi Gupta ✌️Independent ...Russian  Call Girls Delhi Indirapuram {9711199171} Aarvi Gupta ✌️Independent ...
Russian Call Girls Delhi Indirapuram {9711199171} Aarvi Gupta ✌️Independent ...shivangimorya083
 
Innovating Manufacturing with CNC Technology
Innovating Manufacturing with CNC TechnologyInnovating Manufacturing with CNC Technology
Innovating Manufacturing with CNC Technologyquickpartslimitlessm
 
Hot And Sexy 🥵 Call Girls Delhi Daryaganj {9711199171} Ira Malik High class G...
Hot And Sexy 🥵 Call Girls Delhi Daryaganj {9711199171} Ira Malik High class G...Hot And Sexy 🥵 Call Girls Delhi Daryaganj {9711199171} Ira Malik High class G...
Hot And Sexy 🥵 Call Girls Delhi Daryaganj {9711199171} Ira Malik High class G...shivangimorya083
 
John Deere 300 3029 4039 4045 6059 6068 Engine Operation and Service Manual
John Deere 300 3029 4039 4045 6059 6068 Engine Operation and Service ManualJohn Deere 300 3029 4039 4045 6059 6068 Engine Operation and Service Manual
John Deere 300 3029 4039 4045 6059 6068 Engine Operation and Service ManualExcavator
 
如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一
如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一
如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一hnfusn
 
The 10th anniversary, Hyundai World Rally Team's amazing journey
The 10th anniversary, Hyundai World Rally Team's amazing journeyThe 10th anniversary, Hyundai World Rally Team's amazing journey
The 10th anniversary, Hyundai World Rally Team's amazing journeyHyundai Motor Group
 
Dubai Call Girls Size E6 (O525547819) Call Girls In Dubai
Dubai Call Girls  Size E6 (O525547819) Call Girls In DubaiDubai Call Girls  Size E6 (O525547819) Call Girls In Dubai
Dubai Call Girls Size E6 (O525547819) Call Girls In Dubaikojalkojal131
 
Digamma - CertiCon Team Skills and Qualifications
Digamma - CertiCon Team Skills and QualificationsDigamma - CertiCon Team Skills and Qualifications
Digamma - CertiCon Team Skills and QualificationsMihajloManjak
 
Beautiful Vip Call Girls Punjabi Bagh 9711199012 Call /Whatsapps
Beautiful Vip  Call Girls Punjabi Bagh 9711199012 Call /WhatsappsBeautiful Vip  Call Girls Punjabi Bagh 9711199012 Call /Whatsapps
Beautiful Vip Call Girls Punjabi Bagh 9711199012 Call /Whatsappssapnasaifi408
 
John Deere Tractors 5515 Diagnostic Repair Manual
John Deere Tractors 5515 Diagnostic Repair ManualJohn Deere Tractors 5515 Diagnostic Repair Manual
John Deere Tractors 5515 Diagnostic Repair ManualExcavator
 
꧁ ୨⎯Call Girls In Ashok Vihar, New Delhi **✿❀7042364481❀✿**Escorts ServiCes C...
꧁ ୨⎯Call Girls In Ashok Vihar, New Delhi **✿❀7042364481❀✿**Escorts ServiCes C...꧁ ୨⎯Call Girls In Ashok Vihar, New Delhi **✿❀7042364481❀✿**Escorts ServiCes C...
꧁ ୨⎯Call Girls In Ashok Vihar, New Delhi **✿❀7042364481❀✿**Escorts ServiCes C...Hot Call Girls In Sector 58 (Noida)
 
Delhi Call Girls Saket 9711199171 ☎✔👌✔ Full night Service for more than 1 person
Delhi Call Girls Saket 9711199171 ☎✔👌✔ Full night Service for more than 1 personDelhi Call Girls Saket 9711199171 ☎✔👌✔ Full night Service for more than 1 person
Delhi Call Girls Saket 9711199171 ☎✔👌✔ Full night Service for more than 1 personshivangimorya083
 
2024 TOP 10 most fuel-efficient vehicles according to the US agency
2024 TOP 10 most fuel-efficient vehicles according to the US agency2024 TOP 10 most fuel-efficient vehicles according to the US agency
2024 TOP 10 most fuel-efficient vehicles according to the US agencyHyundai Motor Group
 
VDA 6.3 Process Approach in Automotive Industries
VDA 6.3 Process Approach in Automotive IndustriesVDA 6.3 Process Approach in Automotive Industries
VDA 6.3 Process Approach in Automotive IndustriesKannanDN
 
Not Sure About VW EGR Valve Health Look For These Symptoms
Not Sure About VW EGR Valve Health Look For These SymptomsNot Sure About VW EGR Valve Health Look For These Symptoms
Not Sure About VW EGR Valve Health Look For These SymptomsFifth Gear Automotive
 
FULL ENJOY - 9953040155 Call Girls in Sector 61 | Noida
FULL ENJOY - 9953040155 Call Girls in Sector 61 | NoidaFULL ENJOY - 9953040155 Call Girls in Sector 61 | Noida
FULL ENJOY - 9953040155 Call Girls in Sector 61 | NoidaMalviyaNagarCallGirl
 

Recently uploaded (20)

Vip Hot Call Girls 🫤 Mahipalpur ➡️ 9711199171 ➡️ Delhi 🫦 Whatsapp Number
Vip Hot Call Girls 🫤 Mahipalpur ➡️ 9711199171 ➡️ Delhi 🫦 Whatsapp NumberVip Hot Call Girls 🫤 Mahipalpur ➡️ 9711199171 ➡️ Delhi 🫦 Whatsapp Number
Vip Hot Call Girls 🫤 Mahipalpur ➡️ 9711199171 ➡️ Delhi 🫦 Whatsapp Number
 
sauth delhi call girls in Connaught Place🔝 9953056974 🔝 escort Service
sauth delhi call girls in  Connaught Place🔝 9953056974 🔝 escort Servicesauth delhi call girls in  Connaught Place🔝 9953056974 🔝 escort Service
sauth delhi call girls in Connaught Place🔝 9953056974 🔝 escort Service
 
Russian Call Girls Delhi Indirapuram {9711199171} Aarvi Gupta ✌️Independent ...
Russian  Call Girls Delhi Indirapuram {9711199171} Aarvi Gupta ✌️Independent ...Russian  Call Girls Delhi Indirapuram {9711199171} Aarvi Gupta ✌️Independent ...
Russian Call Girls Delhi Indirapuram {9711199171} Aarvi Gupta ✌️Independent ...
 
Indian Downtown Call Girls # 00971528903066 # Indian Call Girls In Downtown D...
Indian Downtown Call Girls # 00971528903066 # Indian Call Girls In Downtown D...Indian Downtown Call Girls # 00971528903066 # Indian Call Girls In Downtown D...
Indian Downtown Call Girls # 00971528903066 # Indian Call Girls In Downtown D...
 
Innovating Manufacturing with CNC Technology
Innovating Manufacturing with CNC TechnologyInnovating Manufacturing with CNC Technology
Innovating Manufacturing with CNC Technology
 
Hot And Sexy 🥵 Call Girls Delhi Daryaganj {9711199171} Ira Malik High class G...
Hot And Sexy 🥵 Call Girls Delhi Daryaganj {9711199171} Ira Malik High class G...Hot And Sexy 🥵 Call Girls Delhi Daryaganj {9711199171} Ira Malik High class G...
Hot And Sexy 🥵 Call Girls Delhi Daryaganj {9711199171} Ira Malik High class G...
 
John Deere 300 3029 4039 4045 6059 6068 Engine Operation and Service Manual
John Deere 300 3029 4039 4045 6059 6068 Engine Operation and Service ManualJohn Deere 300 3029 4039 4045 6059 6068 Engine Operation and Service Manual
John Deere 300 3029 4039 4045 6059 6068 Engine Operation and Service Manual
 
如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一
如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一
如何办理(UQ毕业证书)昆士兰大学毕业证毕业证成绩单原版一比一
 
The 10th anniversary, Hyundai World Rally Team's amazing journey
The 10th anniversary, Hyundai World Rally Team's amazing journeyThe 10th anniversary, Hyundai World Rally Team's amazing journey
The 10th anniversary, Hyundai World Rally Team's amazing journey
 
Dubai Call Girls Size E6 (O525547819) Call Girls In Dubai
Dubai Call Girls  Size E6 (O525547819) Call Girls In DubaiDubai Call Girls  Size E6 (O525547819) Call Girls In Dubai
Dubai Call Girls Size E6 (O525547819) Call Girls In Dubai
 
Digamma - CertiCon Team Skills and Qualifications
Digamma - CertiCon Team Skills and QualificationsDigamma - CertiCon Team Skills and Qualifications
Digamma - CertiCon Team Skills and Qualifications
 
Beautiful Vip Call Girls Punjabi Bagh 9711199012 Call /Whatsapps
Beautiful Vip  Call Girls Punjabi Bagh 9711199012 Call /WhatsappsBeautiful Vip  Call Girls Punjabi Bagh 9711199012 Call /Whatsapps
Beautiful Vip Call Girls Punjabi Bagh 9711199012 Call /Whatsapps
 
John Deere Tractors 5515 Diagnostic Repair Manual
John Deere Tractors 5515 Diagnostic Repair ManualJohn Deere Tractors 5515 Diagnostic Repair Manual
John Deere Tractors 5515 Diagnostic Repair Manual
 
Call Girls In Kirti Nagar 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SERVICE
Call Girls In Kirti Nagar 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SERVICECall Girls In Kirti Nagar 📱  9999965857  🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SERVICE
Call Girls In Kirti Nagar 📱 9999965857 🤩 Delhi 🫦 HOT AND SEXY VVIP 🍎 SERVICE
 
꧁ ୨⎯Call Girls In Ashok Vihar, New Delhi **✿❀7042364481❀✿**Escorts ServiCes C...
꧁ ୨⎯Call Girls In Ashok Vihar, New Delhi **✿❀7042364481❀✿**Escorts ServiCes C...꧁ ୨⎯Call Girls In Ashok Vihar, New Delhi **✿❀7042364481❀✿**Escorts ServiCes C...
꧁ ୨⎯Call Girls In Ashok Vihar, New Delhi **✿❀7042364481❀✿**Escorts ServiCes C...
 
Delhi Call Girls Saket 9711199171 ☎✔👌✔ Full night Service for more than 1 person
Delhi Call Girls Saket 9711199171 ☎✔👌✔ Full night Service for more than 1 personDelhi Call Girls Saket 9711199171 ☎✔👌✔ Full night Service for more than 1 person
Delhi Call Girls Saket 9711199171 ☎✔👌✔ Full night Service for more than 1 person
 
2024 TOP 10 most fuel-efficient vehicles according to the US agency
2024 TOP 10 most fuel-efficient vehicles according to the US agency2024 TOP 10 most fuel-efficient vehicles according to the US agency
2024 TOP 10 most fuel-efficient vehicles according to the US agency
 
VDA 6.3 Process Approach in Automotive Industries
VDA 6.3 Process Approach in Automotive IndustriesVDA 6.3 Process Approach in Automotive Industries
VDA 6.3 Process Approach in Automotive Industries
 
Not Sure About VW EGR Valve Health Look For These Symptoms
Not Sure About VW EGR Valve Health Look For These SymptomsNot Sure About VW EGR Valve Health Look For These Symptoms
Not Sure About VW EGR Valve Health Look For These Symptoms
 
FULL ENJOY - 9953040155 Call Girls in Sector 61 | Noida
FULL ENJOY - 9953040155 Call Girls in Sector 61 | NoidaFULL ENJOY - 9953040155 Call Girls in Sector 61 | Noida
FULL ENJOY - 9953040155 Call Girls in Sector 61 | Noida
 

Here are the main steps in a typical machine learning workflow:1. Data Collection: Collecting and preparing the raw data you'll use to train your model. This may involve cleaning, formatting, feature engineering, etc. 2. Data Exploration: Exploring your data to understand its characteristics and identify any issues. This involves calculating statistics, visualizing relationships, and checking for biases.3. Model Selection: Choosing the machine learning model that is best suited for your problem - supervised vs unsupervised, regression vs classification, etc. 4. Feature Engineering: Transforming raw data into "features" the learning algorithm can use. This may involve discretization, normalization, principal component analysis, etc.5

  • 1. Python으로 IoT(Internet of Things), Cognitive, Machine Learning 3종 셋트 활용하기 김영욱 Evangelist Microsoft / DX / 부장 youngwook@outlook.com
  • 2.
  • 3.
  • 6.
  • 8.
  • 10. PTVS(Python  Tools  for  Visual  Studio) NTVS(Node.js  Tools  for  Visual  Studio) RTVS(R  Tools  for  Visual  Studio) PHP  Tools  for  Visual  Studio Visual  C++  for  Linux
  • 12.
  • 13.
  • 15. Sensors on Linux (Rasberian) SQL Database Machine Learning Power BIStream Analytics IoT Hubs Blob / Table Cognitive Services Microsoft Cognitive Services IoT Service Machine Learning
  • 19. Microsoft 
 Cognitive 
 Services Give your apps 
 a human side Vision From faces to feelings, allow your 
 apps to understand images and video Speech Hear and speak to your users by filtering noise, identifying speakers, and understanding intent Language Process text and learn how to recognize what users want Knowledge Tap into rich knowledge amassed from 
 the web, academia, or your own data Search Access billions of web pages, images, videos, and news with the power of Bing APIs Cognitive Services
  • 20. Apps Powered by MS Cognitive Services ProjectMurphy.n et CaptionBot.ai I think it’s a person sitting in front of a computer and he seems ☺. I am 99% sure that’s Bill Gates Celebslike.me
  • 21. Roll your own with REST APIs Simple to add: just a few lines 
 of code required Make the same API code call on iOS, Android, and Windows Integrate into the language 
 and platform of your choice Built by experts in their field from Microsoft Research, Bing, and Azure Machine Learning Quality documentation, sample code, and community support Easy Flexible Tested GET A
 KEY BUILD Why Microsoft 
 Cognitive Services ?
  • 22. Cognitive Services Emotion Speaker Recognition Speech Custom RecognitionComputer Vision Face Video microsoft.com/cognitive SearchSpeech Language KnowledgeVision Linguistic Analysis Language Understanding Bing Spell Check Entity Linking Knowledge Exploration Academic Knowledge Bing Image Search Bing Video Search Bing Web Search WebLM Text Analytics Recommendations Bing Autosuggest Bing News Search Translator
  • 23. Cognitive Services Emotion Speaker Recognition Speech Custom RecognitionComputer Vision Face Video SearchSpeech Language KnowledgeVision Linguistic Analysis Language Understanding Bing Spell Check Entity Linking Knowledge Exploration Academic Knowledge Bing Image Search Bing Video Search Bing Web Search WebLM Text Analytics Recommendations Bing Autosuggest Bing News Search Translator microsoft.com/cognitive
  • 27.
  • 28. Demo
  • 29. Language
 Bing Spell check
 Language Understanding
 Linguistic Analysis
 Text Analytics 
 WebLM
  • 30.
  • 31. Demo
  • 32. Bing
 Bing Web Search
 Bing Image Search
 Bing Video Search
 Bing News Search
 Bing Autosuggest
  • 33. Bing beyond search in bing.comSmarter, more engaging experiences Trusted by industry- leading experiences
  • 34. Introducing Bing Search API v5 Web Search Image Search Video Search News Search Autosuggest Spell Check Search API v5 REST Enhanced Search and Filtering Capabilities Ongoing Improvements and Support Web- Scale High Performance Secure (HTTPs)
  • 35. Web Search APIWeb Search API *screenshots show actual search results on bing.com https://bingapis.azure-api.net/v5/search? q=nasa Get relevant web and answer results and metadata with one API call { “_type”: “SearchResponse”, “queryContent”: {…}, “webPages”: {…}, “news”: {…}, “images”: {…}, “videos”: {…}, “relatedSearches”: {…}, “rankingResponse”: {…} } { “answerType”:”WebPages”, “resultIndex”:0,… }, { “answerType”:”News”, “resultIndex”:1,… } Ranking Response Search Response Web Results Deep Links (1st Algo) News Results Image Results Video Results Related Searches
  • 36. Vertical Search APIs https://bingapis.azure-api.net/v5/images/search?q=shuttle +launch • Enhanced metadata and filters (size, license, style, freshness, color) • Image insights (entity recognition, visually similar) Image Search API source: nasa.gov https://bingapis.azure-api.net/v5/videos/search?q=viral+videos • Enhanced metadata and filters (price, resolution, length, freshness) • Motion thumbnails (video preview) https://bingapis.azure-api.net/v5/news/search?q=cuba • News by category/market, and trending news • Rich article metadata (featured entities) source: youtube.com Video Search API *screenshots show actual search results in bing.com Get more results, features and metadata tailored to each search vertical News Search API source: cnn.com
  • 37. Demo
  • 38. • Sign up and get started today for free at www.microsoft.com/cognitive Developer Call to Action
  • 40. Sensors on Linux (Rasberian) SQL Database Machine Learning Power BIStream Analytics IoT Hubs Blob / Table Cognitive Services Microsoft Cognitive Services IoT Service Machine Learning
  • 41. • 지원되는 프로토콜은 HTTP1.1, MQTT, AMQP 1.0 (16년 4월 OPC 공식지원 발표) • LWM2M, CoAP 등의 지원은 계획 중이나 시기 미정 IoT Hub
  • 43. Sensors on Linux (Rasberian) SQL Database Machine Learning Power BIStream Analytics IoT Hubs Blob / Table Cognitive Services Microsoft Cognitive Services IoT Service Machine Learning
  • 45.
  • 46. Microsoft & Machine Learning
 15 years of realizing innovation SQL Server enables 
 data mining Computers work on users behalf, filtering junk email Microsoft Kinect can watch users gestures Microsoft launches 
 Azure Machine Learning Microsoft search engine built with machine learning Bing Maps ships with ML traffic- prediction service Successful, real-time, speech-to- speech translation John Platt, 
 Distinguished scientist at Microsoft Research 1999 201220082004 201420102005 Machine learning is pervasive throughout 
 Microsoft products.“ ”
  • 47. One solution for Machine Learning - from data to results Azure Portal Azure Ops Team ML Studio Data Scientist HDInsight Azure Storage Desktop Data Azure Portal & 
 ML API service Azure Ops Team PowerBI/ Dashboards Mobile AppsWeb Apps ML API service Developer
  • 48. Machine Learning Data I/O Taking Data & preparing for Analysis Dimensionality reduction. E.g. Kinect measures 1000 points, 6 are relevant Fitting Model selection; calibration; assessment R – free scripts/graphics, many packages based on Vector Data. Metrics to allow us to describe the data. E.g. Mean, Correlation… Tools used for Text Input. E.g. ‘What is the theme of this essay?’