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
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
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)
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
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
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
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
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?’