What email address or phone number would you like to use to sign in to Docs.com?
If you already have an account that you use with Office or other Microsoft services, enter it here.
Or sign in with:
Signing in allows you to download and like content, and it provides the authors analytical data about your interactions with their content.
Embed code for: "Something" worth ten Microsofts - Azure ML 101
Select a size
Azure Machine learning is a fully managed cloud service that enables you to easily build, deploy, and share predictive analytics solutions. Here's a jump start for Azure ML.
‘Something’ worth ten Microsofts
Software Engineer – Data Science & Analytics | Tech One Global Pvt. Ltd
CRISP - DM
No coding! Seriously??
Top class machine learning algorithms inbuilt.
Power of cloud.
Easy deployment with RESTful API.
R & Python support
You heard hell a lot on AzureML that you couldn’t believe, and now it’s time for a DEMO
Caution : Unexpected things may occur during a demonstration
Iris Flower Dataset
A fully managed cloud service that enables you to easily build, deploy, and share predictive analytics solutions.
Cortana Intelligence is a powerful solution to transform your data into intelligent action from Microsoft.
Machine learning is a scientific discipline that deals with the construction and study of algorithms that can learn from data.
Such algorithms operate by building a model based on inputs and using that to make predictions or decisions, rather than following only explicitly programmed instructions.
Face detection: The face detection feature in mobile cameras is an example of what machine learning can do. Cameras can automatically snap a photo when someone smiles more accurately now than ever before because of advances in machine learning algorithms.
Face recognition: This is where a computer program can identify an individual from a photo. You can find this feature on Facebook for automatically tagging people in photos where they appear. Advances in machine learning means more accurate auto-face tagging software.
Image classification: A good example is the application of deep learning to improve image classification or image categorization in apps such as Google photos. Google photos would not be possible without advances in deep learning.
Speech recognition: Another good example is Google now. Improvements in speech recognition systems has been made possible by, you guessed right, machine learning specifically deep learning.
Google: Google defines itself as a machine learning company now. It is also a leader in this area because machine learning is a very important component to it's core advertising and search businesses. It applies machine learning to improve search results and search suggestions.
Anti-virus: Machine learning is used in Anti-virus softwares to improve detection of malicious software on computer devices.
Anti-spam: machine learning is also used to train better anti-spam software systems.
Genetics: Classical data mining or clustering algorithms in machine learning such as agglomerative clustering algorithms are used in genetics to help find genes associated with a particular disease.
Signal denoising: Machine learning algorithms such as the K-SVD which is just a generalization of k-means clustering are used to find a dictionary of vectors that can be sparsely linearly combined to approximate any given input signal. Thus such a technique is used in video compression and denoising.
Weather forecast: Machine learning is applied in weather forecasting software to improve the quality of the forecast.
Cross Industry Standard Process for Data Mining - data mining process model that describes commonly used approaches that data mining experts use to tackle problems.
Azure machine learning process. Starts with defining the objective.
Demo would be building a multiclass classification for Iris dataset.
Dataset is grabbed from UCI machine learning repository.
These are the three classes that need to be predicted
With machine learning, you can’t get 100% accuracy. If you getting close to 100% it should surely be overfitting.