SlideShare a Scribd company logo
1 of 23
Download to read offline
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Michal Brys
Senior Data Scientist @ Mezzobit
DevFestPL | Warsaw, 26th November 2016
Cloud
Machine Learning
Introduction
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Michał Bryś
Senior Data Scientist @ Mezzobit
michalbrys.com
@michalbrys
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Machine Learning - basics
Supervised
i.e. classify object to
known pattern.
Unsupervised
i.e. divide set with prior
unknown pattern
Reinforcement
algorithm
learns to react
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
https://www.wired.com/2016/03/two-moves-alphago-lee-sedol-redefined-future/
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
http://spectrum.ieee.org/cars-that-think/transportation/self-driving/new-pedestrian
-detector-from-google-could-make-selfdriving-cars-cheaper
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Academic / Research
Industry / Applications
Source: Google Next Conference London 2016
Tensor Flow Cloud Machine Learning Machine Learning APIs
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Source: Google Next Conference London 2016
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
How can I use it
in my projects?
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Academic / Research
Industry / Applications
Source: Google Next Conference London 2016
Tensor Flow Cloud Machine Learning Machine Learning APIs
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
All you need to start:
Natural Language API
Jobs API
Speech API
Translate API
Vision API
Cloud Machine
Learning Platform
+
Compute engine
Cloud Storage
Big Query
Cloud Datalabs
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Natural Language API
Case study:
Sentiment analysis
of hotel reviews
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Sentiment analysis
Review:
The staff was very friendly and I was pleasantly surprised at
how clean and refreshing our room was. Great stay!
Score: 0.9
ranges between -1.0 (negative) and 1.0 (positive)
Magnitude: 0.9
overall strength of emotion within the given text, between 0.0 and +inf
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Collect hotel reviews (1)
scrapy crawl tripadvisor -o hotels.txt -s CLOSESPIDER_ITEMCOUNT=15000
The staff was very friendly and I was pleasantly surprised at how clean and
refreshing our room was. Great stay!
Really large apartment fitted out with full size kitchen and appliances (stove,
oven, microwave and full size fridge freezer)
...
https://goo.gl/84rTkT
Compute engine
+ Python, Scrapy
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Score sentiment of review (2)
python sentiment_analysis.py ./resources/hotels.txt
Sentence 0 has a sentiment score of 0.1
Sentence 1 has a sentiment score of -0.3
Sentence 2 has a sentiment score of 0.2
Sentence 3 has a sentiment score of 0.5
Sentence 4 has a sentiment score of 0.6
Sentence 5 has a sentiment score of 0.4
...
Overall Sentiment: score of 0.5 with magnitude of 72.8
https://goo.gl/DQzkZd
Compute engine
+ Python, Natural Language API
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Save results (3)
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Analyze (4)
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Analyze (4)
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
● GCP - Powerful platform for data analysis
Summary
● Out-of-the-box trained Machine Learning models
○ Natural Language
○ Speech
○ Computer Vision
● Use Machine Learning in your apps!
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
quickdraw.withgoogle.com
Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
Michal Brys
michal.brys@gmail.com
@michalbrys
[E-book]: Using Google Analytics with R
michalbrys.com/book

More Related Content

What's hot

Adam Bartusiak and Jörg Lässig | Semantic Processing for the Conversion of Un...
Adam Bartusiak and Jörg Lässig | Semantic Processing for the Conversion of Un...Adam Bartusiak and Jörg Lässig | Semantic Processing for the Conversion of Un...
Adam Bartusiak and Jörg Lässig | Semantic Processing for the Conversion of Un...semanticsconference
 
MuseoTorino, first italian project using a GraphDB, RDFa, Linked Open Data
MuseoTorino, first italian project using a GraphDB, RDFa, Linked Open DataMuseoTorino, first italian project using a GraphDB, RDFa, Linked Open Data
MuseoTorino, first italian project using a GraphDB, RDFa, Linked Open Data21Style
 
Graph-based Network & IT Management.
Graph-based Network & IT Management.Graph-based Network & IT Management.
Graph-based Network & IT Management.Linkurious
 
معرفی کاربردهای یادگیری عمیق و چالش های آن در کلان داده
معرفی کاربردهای یادگیری عمیق و چالش های آن در کلان دادهمعرفی کاربردهای یادگیری عمیق و چالش های آن در کلان داده
معرفی کاربردهای یادگیری عمیق و چالش های آن در کلان دادهWeb Standards School
 
Evolving the Web into a Global Dataspace – Advances and Applications
Evolving the Web into a Global Dataspace – Advances and ApplicationsEvolving the Web into a Global Dataspace – Advances and Applications
Evolving the Web into a Global Dataspace – Advances and ApplicationsChris Bizer
 
Extending Tables with Data from over a Million Websites
 Extending Tables with Data from over a Million Websites Extending Tables with Data from over a Million Websites
Extending Tables with Data from over a Million WebsitesChris Bizer
 
Data Curation @ SpazioDati - NEXA Lunch Seminar
Data Curation @ SpazioDati - NEXA Lunch SeminarData Curation @ SpazioDati - NEXA Lunch Seminar
Data Curation @ SpazioDati - NEXA Lunch SeminarSpazioDati
 
Graph technology and data-journalism: the case of the Paradise Papers
Graph technology and data-journalism: the case of the Paradise PapersGraph technology and data-journalism: the case of the Paradise Papers
Graph technology and data-journalism: the case of the Paradise PapersLinkurious
 
Fast Data processing with RFX
Fast Data processing with RFXFast Data processing with RFX
Fast Data processing with RFXTrieu Nguyen
 
Using Linkurious in your Enterprise Architecture projects
Using Linkurious in your Enterprise Architecture projectsUsing Linkurious in your Enterprise Architecture projects
Using Linkurious in your Enterprise Architecture projectsLinkurious
 
Using graph technology for multi-INT investigations
Using graph technology for multi-INT investigationsUsing graph technology for multi-INT investigations
Using graph technology for multi-INT investigationsLinkurious
 
Web scraping
Web scrapingWeb scraping
Web scrapingSelecto
 
Linked Open Data Utrecht University Library
Linked Open Data Utrecht University LibraryLinked Open Data Utrecht University Library
Linked Open Data Utrecht University LibraryRuben Schalk
 
Informal presentation about RES
Informal presentation about RESInformal presentation about RES
Informal presentation about RESChristophe Guéret
 
Linked data experience at Macmillan: Building discovery services for scientif...
Linked data experience at Macmillan: Building discovery services for scientif...Linked data experience at Macmillan: Building discovery services for scientif...
Linked data experience at Macmillan: Building discovery services for scientif...Michele Pasin
 
Big dataintegration rahm-part3Scalable and privacy-preserving data integratio...
Big dataintegration rahm-part3Scalable and privacy-preserving data integratio...Big dataintegration rahm-part3Scalable and privacy-preserving data integratio...
Big dataintegration rahm-part3Scalable and privacy-preserving data integratio...ErhardRahm
 
Cloud architectures for data science
Cloud architectures for data scienceCloud architectures for data science
Cloud architectures for data scienceMargriet Groenendijk
 

What's hot (19)

Adam Bartusiak and Jörg Lässig | Semantic Processing for the Conversion of Un...
Adam Bartusiak and Jörg Lässig | Semantic Processing for the Conversion of Un...Adam Bartusiak and Jörg Lässig | Semantic Processing for the Conversion of Un...
Adam Bartusiak and Jörg Lässig | Semantic Processing for the Conversion of Un...
 
MuseoTorino, first italian project using a GraphDB, RDFa, Linked Open Data
MuseoTorino, first italian project using a GraphDB, RDFa, Linked Open DataMuseoTorino, first italian project using a GraphDB, RDFa, Linked Open Data
MuseoTorino, first italian project using a GraphDB, RDFa, Linked Open Data
 
Graph-based Network & IT Management.
Graph-based Network & IT Management.Graph-based Network & IT Management.
Graph-based Network & IT Management.
 
معرفی کاربردهای یادگیری عمیق و چالش های آن در کلان داده
معرفی کاربردهای یادگیری عمیق و چالش های آن در کلان دادهمعرفی کاربردهای یادگیری عمیق و چالش های آن در کلان داده
معرفی کاربردهای یادگیری عمیق و چالش های آن در کلان داده
 
Evolving the Web into a Global Dataspace – Advances and Applications
Evolving the Web into a Global Dataspace – Advances and ApplicationsEvolving the Web into a Global Dataspace – Advances and Applications
Evolving the Web into a Global Dataspace – Advances and Applications
 
Extending Tables with Data from over a Million Websites
 Extending Tables with Data from over a Million Websites Extending Tables with Data from over a Million Websites
Extending Tables with Data from over a Million Websites
 
Data Curation @ SpazioDati - NEXA Lunch Seminar
Data Curation @ SpazioDati - NEXA Lunch SeminarData Curation @ SpazioDati - NEXA Lunch Seminar
Data Curation @ SpazioDati - NEXA Lunch Seminar
 
Graph technology and data-journalism: the case of the Paradise Papers
Graph technology and data-journalism: the case of the Paradise PapersGraph technology and data-journalism: the case of the Paradise Papers
Graph technology and data-journalism: the case of the Paradise Papers
 
Fast Data processing with RFX
Fast Data processing with RFXFast Data processing with RFX
Fast Data processing with RFX
 
Data Science in the Cloud
Data Science in the CloudData Science in the Cloud
Data Science in the Cloud
 
Using Linkurious in your Enterprise Architecture projects
Using Linkurious in your Enterprise Architecture projectsUsing Linkurious in your Enterprise Architecture projects
Using Linkurious in your Enterprise Architecture projects
 
Using graph technology for multi-INT investigations
Using graph technology for multi-INT investigationsUsing graph technology for multi-INT investigations
Using graph technology for multi-INT investigations
 
Linked Data Tutorial
Linked Data TutorialLinked Data Tutorial
Linked Data Tutorial
 
Web scraping
Web scrapingWeb scraping
Web scraping
 
Linked Open Data Utrecht University Library
Linked Open Data Utrecht University LibraryLinked Open Data Utrecht University Library
Linked Open Data Utrecht University Library
 
Informal presentation about RES
Informal presentation about RESInformal presentation about RES
Informal presentation about RES
 
Linked data experience at Macmillan: Building discovery services for scientif...
Linked data experience at Macmillan: Building discovery services for scientif...Linked data experience at Macmillan: Building discovery services for scientif...
Linked data experience at Macmillan: Building discovery services for scientif...
 
Big dataintegration rahm-part3Scalable and privacy-preserving data integratio...
Big dataintegration rahm-part3Scalable and privacy-preserving data integratio...Big dataintegration rahm-part3Scalable and privacy-preserving data integratio...
Big dataintegration rahm-part3Scalable and privacy-preserving data integratio...
 
Cloud architectures for data science
Cloud architectures for data scienceCloud architectures for data science
Cloud architectures for data science
 

Viewers also liked

Google Analytics + R. Praktyczne przykłady.
Google Analytics + R. Praktyczne przykłady.Google Analytics + R. Praktyczne przykłady.
Google Analytics + R. Praktyczne przykłady.Michal Brys
 
Google Analytics + R
Google Analytics + RGoogle Analytics + R
Google Analytics + RMichal Brys
 
Google dla serwisów e-commerce. Porady Praktyczne.
Google dla serwisów e-commerce. Porady Praktyczne.Google dla serwisów e-commerce. Porady Praktyczne.
Google dla serwisów e-commerce. Porady Praktyczne.Michal Brys
 
Web users tracking behind the scenes
Web users tracking behind the scenesWeb users tracking behind the scenes
Web users tracking behind the scenesMichal Brys
 
Bigdata w serwisach e-commerce z wykorzystaniem narzędzi Google
Bigdata w serwisach e-commerce z wykorzystaniem narzędzi GoogleBigdata w serwisach e-commerce z wykorzystaniem narzędzi Google
Bigdata w serwisach e-commerce z wykorzystaniem narzędzi GoogleMichal Brys
 
Find signal in noise.
Find signal in noise.Find signal in noise.
Find signal in noise.Michal Brys
 
Poznaj lepiej użytkowników Twojego serwisu z Google Analytics
Poznaj lepiej użytkowników Twojego serwisu z Google AnalyticsPoznaj lepiej użytkowników Twojego serwisu z Google Analytics
Poznaj lepiej użytkowników Twojego serwisu z Google AnalyticsMichal Brys
 

Viewers also liked (7)

Google Analytics + R. Praktyczne przykłady.
Google Analytics + R. Praktyczne przykłady.Google Analytics + R. Praktyczne przykłady.
Google Analytics + R. Praktyczne przykłady.
 
Google Analytics + R
Google Analytics + RGoogle Analytics + R
Google Analytics + R
 
Google dla serwisów e-commerce. Porady Praktyczne.
Google dla serwisów e-commerce. Porady Praktyczne.Google dla serwisów e-commerce. Porady Praktyczne.
Google dla serwisów e-commerce. Porady Praktyczne.
 
Web users tracking behind the scenes
Web users tracking behind the scenesWeb users tracking behind the scenes
Web users tracking behind the scenes
 
Bigdata w serwisach e-commerce z wykorzystaniem narzędzi Google
Bigdata w serwisach e-commerce z wykorzystaniem narzędzi GoogleBigdata w serwisach e-commerce z wykorzystaniem narzędzi Google
Bigdata w serwisach e-commerce z wykorzystaniem narzędzi Google
 
Find signal in noise.
Find signal in noise.Find signal in noise.
Find signal in noise.
 
Poznaj lepiej użytkowników Twojego serwisu z Google Analytics
Poznaj lepiej użytkowników Twojego serwisu z Google AnalyticsPoznaj lepiej użytkowników Twojego serwisu z Google Analytics
Poznaj lepiej użytkowników Twojego serwisu z Google Analytics
 

Similar to Cloud Machine Learning with Google Cloud Platform

What is Power BI
What is Power BIWhat is Power BI
What is Power BIDries Vyvey
 
Azure machine learning ile tahminleme modelleri
Azure machine learning ile tahminleme modelleriAzure machine learning ile tahminleme modelleri
Azure machine learning ile tahminleme modelleriKoray Kocabas
 
Analytycs fot iot_hen_we_tv1
Analytycs fot iot_hen_we_tv1Analytycs fot iot_hen_we_tv1
Analytycs fot iot_hen_we_tv1Roy Cecil
 
How to get prepared for Syntex
How to get prepared for SyntexHow to get prepared for Syntex
How to get prepared for SyntexNicolas Georgeault
 
Creating Data Visualisations for the Web
Creating Data Visualisations for the WebCreating Data Visualisations for the Web
Creating Data Visualisations for the WebEmpathyBroker
 
Democratizing Artificial Intelligence
Democratizing Artificial IntelligenceDemocratizing Artificial Intelligence
Democratizing Artificial IntelligenceDmitry Petukhov
 
Microsoft IoT & Data OpenHack Zürich
Microsoft IoT & Data OpenHack ZürichMicrosoft IoT & Data OpenHack Zürich
Microsoft IoT & Data OpenHack ZürichSascha Corti
 
Leveraging Data Driven Research Through Microsoft Azure
Leveraging Data Driven Research Through Microsoft AzureLeveraging Data Driven Research Through Microsoft Azure
Leveraging Data Driven Research Through Microsoft AzureMiguel González-Fierro
 
Develop intelligent apps for the modern workplace
Develop intelligent apps for the modern workplaceDevelop intelligent apps for the modern workplace
Develop intelligent apps for the modern workplaceatwork
 
Microsoft AI Platform - AETHER Introduction
Microsoft AI Platform - AETHER IntroductionMicrosoft AI Platform - AETHER Introduction
Microsoft AI Platform - AETHER IntroductionKarthik Murugesan
 
Building High-Quality Datasets & Computer Vision Models with FiftyOne
Building High-Quality Datasets & Computer Vision Models with FiftyOneBuilding High-Quality Datasets & Computer Vision Models with FiftyOne
Building High-Quality Datasets & Computer Vision Models with FiftyOneMichelleBrinich1
 
Future of AI: Blockchain & Deep Learning
Future of AI: Blockchain & Deep LearningFuture of AI: Blockchain & Deep Learning
Future of AI: Blockchain & Deep LearningMelanie Swan
 
OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018
OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018
OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018OW2
 
AI @ Microsoft, How we do it and how you can too!
AI @ Microsoft, How we do it and how you can too!AI @ Microsoft, How we do it and how you can too!
AI @ Microsoft, How we do it and how you can too!Microsoft Tech Community
 
SharePoint Syntex from an Architects Perspective
SharePoint Syntex from an Architects PerspectiveSharePoint Syntex from an Architects Perspective
SharePoint Syntex from an Architects PerspectiveChris Bortlik
 
[第45回 Machine Learning 15minutes! Broadcast] Azure AI - Build 2020 Updates
[第45回 Machine Learning 15minutes! Broadcast] Azure AI - Build 2020 Updates[第45回 Machine Learning 15minutes! Broadcast] Azure AI - Build 2020 Updates
[第45回 Machine Learning 15minutes! Broadcast] Azure AI - Build 2020 UpdatesNaoki (Neo) SATO
 
China Digital Economy
China Digital EconomyChina Digital Economy
China Digital EconomyMelanie Swan
 

Similar to Cloud Machine Learning with Google Cloud Platform (20)

What is Power BI
What is Power BIWhat is Power BI
What is Power BI
 
Azure machine learning ile tahminleme modelleri
Azure machine learning ile tahminleme modelleriAzure machine learning ile tahminleme modelleri
Azure machine learning ile tahminleme modelleri
 
Analytycs fot iot_hen_we_tv1
Analytycs fot iot_hen_we_tv1Analytycs fot iot_hen_we_tv1
Analytycs fot iot_hen_we_tv1
 
How to get prepared for Syntex
How to get prepared for SyntexHow to get prepared for Syntex
How to get prepared for Syntex
 
Creating Data Visualisations for the Web
Creating Data Visualisations for the WebCreating Data Visualisations for the Web
Creating Data Visualisations for the Web
 
Democratizing Artificial Intelligence
Democratizing Artificial IntelligenceDemocratizing Artificial Intelligence
Democratizing Artificial Intelligence
 
Microsoft IoT & Data OpenHack Zürich
Microsoft IoT & Data OpenHack ZürichMicrosoft IoT & Data OpenHack Zürich
Microsoft IoT & Data OpenHack Zürich
 
Leveraging Data Driven Research Through Microsoft Azure
Leveraging Data Driven Research Through Microsoft AzureLeveraging Data Driven Research Through Microsoft Azure
Leveraging Data Driven Research Through Microsoft Azure
 
Mp resume
Mp resumeMp resume
Mp resume
 
Develop intelligent apps for the modern workplace
Develop intelligent apps for the modern workplaceDevelop intelligent apps for the modern workplace
Develop intelligent apps for the modern workplace
 
Microsoft AI Platform - AETHER Introduction
Microsoft AI Platform - AETHER IntroductionMicrosoft AI Platform - AETHER Introduction
Microsoft AI Platform - AETHER Introduction
 
Building High-Quality Datasets & Computer Vision Models with FiftyOne
Building High-Quality Datasets & Computer Vision Models with FiftyOneBuilding High-Quality Datasets & Computer Vision Models with FiftyOne
Building High-Quality Datasets & Computer Vision Models with FiftyOne
 
Data mining projects
Data mining projectsData mining projects
Data mining projects
 
Future of AI: Blockchain & Deep Learning
Future of AI: Blockchain & Deep LearningFuture of AI: Blockchain & Deep Learning
Future of AI: Blockchain & Deep Learning
 
OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018
OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018
OSS Projects Knowledge Mining with CROSSMINER, OW2con'18, June 7-8, 2018
 
AI @ Microsoft, How we do it and how you can too!
AI @ Microsoft, How we do it and how you can too!AI @ Microsoft, How we do it and how you can too!
AI @ Microsoft, How we do it and how you can too!
 
SharePoint Syntex from an Architects Perspective
SharePoint Syntex from an Architects PerspectiveSharePoint Syntex from an Architects Perspective
SharePoint Syntex from an Architects Perspective
 
Alok Ranjan Bhoi
Alok Ranjan BhoiAlok Ranjan Bhoi
Alok Ranjan Bhoi
 
[第45回 Machine Learning 15minutes! Broadcast] Azure AI - Build 2020 Updates
[第45回 Machine Learning 15minutes! Broadcast] Azure AI - Build 2020 Updates[第45回 Machine Learning 15minutes! Broadcast] Azure AI - Build 2020 Updates
[第45回 Machine Learning 15minutes! Broadcast] Azure AI - Build 2020 Updates
 
China Digital Economy
China Digital EconomyChina Digital Economy
China Digital Economy
 

Recently uploaded

Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure servicePooja Nehwal
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 

Recently uploaded (20)

Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 

Cloud Machine Learning with Google Cloud Platform

  • 1. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Michal Brys Senior Data Scientist @ Mezzobit DevFestPL | Warsaw, 26th November 2016 Cloud Machine Learning Introduction
  • 2. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Michał Bryś Senior Data Scientist @ Mezzobit michalbrys.com @michalbrys
  • 3. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
  • 4. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Machine Learning - basics Supervised i.e. classify object to known pattern. Unsupervised i.e. divide set with prior unknown pattern Reinforcement algorithm learns to react
  • 5. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 https://www.wired.com/2016/03/two-moves-alphago-lee-sedol-redefined-future/
  • 6. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 http://spectrum.ieee.org/cars-that-think/transportation/self-driving/new-pedestrian -detector-from-google-could-make-selfdriving-cars-cheaper
  • 7. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
  • 8. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Academic / Research Industry / Applications Source: Google Next Conference London 2016 Tensor Flow Cloud Machine Learning Machine Learning APIs
  • 9. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Source: Google Next Conference London 2016
  • 10. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 How can I use it in my projects?
  • 11. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Academic / Research Industry / Applications Source: Google Next Conference London 2016 Tensor Flow Cloud Machine Learning Machine Learning APIs
  • 12. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016
  • 13. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 All you need to start: Natural Language API Jobs API Speech API Translate API Vision API Cloud Machine Learning Platform + Compute engine Cloud Storage Big Query Cloud Datalabs
  • 14. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Natural Language API Case study: Sentiment analysis of hotel reviews
  • 15. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Sentiment analysis Review: The staff was very friendly and I was pleasantly surprised at how clean and refreshing our room was. Great stay! Score: 0.9 ranges between -1.0 (negative) and 1.0 (positive) Magnitude: 0.9 overall strength of emotion within the given text, between 0.0 and +inf
  • 16. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Collect hotel reviews (1) scrapy crawl tripadvisor -o hotels.txt -s CLOSESPIDER_ITEMCOUNT=15000 The staff was very friendly and I was pleasantly surprised at how clean and refreshing our room was. Great stay! Really large apartment fitted out with full size kitchen and appliances (stove, oven, microwave and full size fridge freezer) ... https://goo.gl/84rTkT Compute engine + Python, Scrapy
  • 17. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Score sentiment of review (2) python sentiment_analysis.py ./resources/hotels.txt Sentence 0 has a sentiment score of 0.1 Sentence 1 has a sentiment score of -0.3 Sentence 2 has a sentiment score of 0.2 Sentence 3 has a sentiment score of 0.5 Sentence 4 has a sentiment score of 0.6 Sentence 5 has a sentiment score of 0.4 ... Overall Sentiment: score of 0.5 with magnitude of 72.8 https://goo.gl/DQzkZd Compute engine + Python, Natural Language API
  • 18. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Save results (3)
  • 19. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Analyze (4)
  • 20. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Analyze (4)
  • 21. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 ● GCP - Powerful platform for data analysis Summary ● Out-of-the-box trained Machine Learning models ○ Natural Language ○ Speech ○ Computer Vision ● Use Machine Learning in your apps!
  • 22. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 quickdraw.withgoogle.com
  • 23. Michał Bryś, Data Scientist @ Allegro, Complexity Garage @ Kraków, 05.02.2016Michal Brys, Senior Data Scientist @ Mezzobit, DevFestPL 2016 Michal Brys michal.brys@gmail.com @michalbrys [E-book]: Using Google Analytics with R michalbrys.com/book