Skip to content

Latest commit

 

History

History
472 lines (324 loc) · 31.4 KB

AI-ML-resources.md

File metadata and controls

472 lines (324 loc) · 31.4 KB

List of Microsoft's Artificial Intelligence and Machine Learning resources

Data Science Blogs


Azure Databricks

Fast, easy, and collaborative Apache Spark-based analytics platform. Accelerate innovation by enabling data science with a high-performance analytics platform that’s optimized for Azure.


Microsoft Machine Learning Services

The goal of the Microsoft Machine Learning Services is to provide an extensible, scalable platform for integrating machine learning tasks and tools with the applications that consume machine learning services. The platform must serve the needs of all users involved in the data development and analytics process, from data scientists, to architects and database adminstrators.


Microsoft's Cognitive Toolkit (CNTK)

A free, easy-to-use, open-source, commercial-grade toolkit that trains deep learning algorithms to learn like the human brain. Coolest part (at least to me) - offers a Python API!


Azure Machine Learning Workbench

Azure Machine Learning is an integrated, end-to-end data science and advanced analytics solution. It helps professional data scientists to prepare data, develop experiments, and deploy models at cloud scale.


AI Tools for VS Code

Visual Studio Code Tools for AI is a cross-platform extension that supports deep learning frameworks including Microsoft Cognitive Toolkit (CNTK), Google Tensorflow, Theano, Keras, Caffe2, and more. You can use additional deep learning frameworks via the open architecture. Visual Studio Code Tools for AI leverages existing code support for Python, C/C++/C#, and supplies additional support for Cognitive Toolkit BrainScript.


Microsoft Azure Machine Learning Studio


Cognitive Services

Infuse your apps, websites, and bots with intelligent algorithms to see, hear, speak, understand and interpret your user needs through natural methods of communication.

Image processing algorithms to smartly identify, caption, and moderate your pictures.

Extract rich information from images to categorize and process visual data, and use machine-assisted moderation of images to help curate your services. Analyze an image, automatically read text in images, read handwritten text, recognize celebrities and landmarks, analyze video in near real-time, generate thumbnails, and more.


Machine-assisted moderation of text and images, augmented with human review tools.

Image Moderation

Enhance your ability to detect potentially offensive or unwanted images through machine-learning based classifiers, custom blacklists, and optical character recognition.

Text Moderation

Helps you detect potential profanity in more than 100 languages and match text against your custom lists automatically. Content Moderator also checks for possible personally identifiable information (PII).

Video Moderation

Enable the scoring of possible adult content in videos. Video moderation is currently deployed in preview on Azure Media Services.

Human Review Tool

Humans can effectively augment machine learning models in situations where the prediction confidence warrants assistance or when decisions must be tempered with a real world context. Enjoy visibility, flexibility and control with a human review tool that supervises the results of your algorithms.


Easily customzie your own state-of-the-art computer vision models for you unique use case.


Detect, identify, analyze, organize, and tag faces in photos. Face verification, similar face search, and face grouping.


Personalize user experiences with emotion recognition. Analyze faces to detect a range of feelings and personalize your app's responses. The Emotion API takes a facial expression in an image as an input, and returns the confidence across a set of emotions for each face in the image, as well as bounding box for the face, using the Face API. If a user has already called the Face API, they can submit the face rectangle as an optional input.


Video Indexer is a cloud service that enables you to transcribe videos, track and ID faces, index speakers, recognize text and scenes, translate in real-time, annotate, and more.


Map complex information and data in order to solve tasks such as intelligent recommendations and semantic search.

Learn from previous transactions to predict which items are more likely to be of interest to or purchased by your customers. Built using Azure Machine Learning, the Recommendations engine uses customer data—either past customer activity you’ve uploaded or data collected directly from your digital store—to offer recommended items for your customers and increase conversion rates.


Enable interactive search experiences over structured data via natural language inputs. Supports natural language understanding, query auto-completion, structured query evaluation, and attribute histograms.


In different contexts, a word might be used as a named entity, a verb, or another word form within a given sentence. For example, in the case where “times” is a named entity, it may refer to two separately distinguishable entities such as “The New York Times” or “Times Square”. Given a specific paragraph of text within a document, the Entity Linking Intelligence Service will recognize and identify each separate entity based on the context.


Tap into the wealth of academic content in the Microsoft Academic Graph using the Academic Knowledge API. Supports interpretation of query strings, evaluation of query expressions, calchistograms, similarity detection, and graph search.


Distill question and answer information into an easy-to-navigate FAQ.


A cloud-based, contextual decision-making API that sharpens with experience.


Allow your apps to process natural language with pre-built scripts, evaluate sentiment, and learn how to recognize what users want.

One of the key problems in human-computer interactions is the ability of the computers to understand what a person wants, and to find the pieces of information that are relevant to his/her intention. Our Language Understanding intelligent service, LUIS, provides simple tools that enable you to build your own language models (intents/entities) which allow any application/bot to understand your commands and act accordingly... Now, try our demo to visualize some of the usage scenarios relaying on LUIS.


Detect and correct spelling mistakes in your app - word breaks, slang, names, homonyms, and brands.


Automate a variety of standard natural language processing tasks using state-of-the-art language modeling APIs. Supports word breaking, next word completions, and joint / conditional probabilities.


Detect sentiment, key phrases, topics, and language from your text.


Automatically detect languages, crowd-source translation improvement, and conduct real-time text translation with a simple REST API call.


The Linguistic Analysis API can tap into traditional linguistic analysis tools that allow you to identify the concepts and actions in your text with part-of-speech tagging, and find phrases and concepts using natural language parsers. Whether you’re mining customer feedback, interpreting user commands, or consuming web text, understanding the structure of the text is a critical first step.


Convert spoken audio into text, use voice for verification, or add speaker recognition to your app.

Easily add speech translation and transcription to your app, optimized for real-life conversation.


Convert spoken audio to text. The API can be directed to turn on and recognize audio coming from the microphone in real-time, recognize audio coming from a different real-time audio source, or to recognize audio from within a file. In all cases, real-time streaming is available, so as the audio is being sent to the server, partial recognition results are also being returned.

The Speech to Text API enables you to build smart apps that are voice triggered. To see how it works select your target language then click on the microphone and start speaking. Or simply click on one of the sample speech phrases to see how speech recognition works. When you use this demo you consent to providing your voice input data to Microsoft for service improvement purpose


Identify individual speakers or use speech as a means of authentication with the Speaker Recognition API.


Overcome speech recognition barriers such as speaking style, vocabulary and background noise. Create custom language and acoustic models.


Add Bing Search APIs to your apps and harness the ability to comb billions of webpages, images, videos, and news with a single API call.


Empower users to type less and do more with automated and complete search suggestions.


Turn any app or website into a news search resource with world news grouped and filtered by topic, local news, and searchable metadata.


Bring intelligent search to your apps and harness the ability to comb billions of webpages, images, videos, and news with a single API call. Retrieve web documents and narrow down the results by type, freshness, and more.


Bing Entity Search API will identify the most relevant entity based on your searched term, spanning multiple entity types such as famous people, places, movies, TV shows, video games, books, and even local businesses near you.


Scour the web for images! Includes thumbnails, full image URLs, publishing website info, image metadata, and more. There are also sorting and filtering options that simplify finding specific results in image searches and enable paging of results.


Add a variety of advanced video search features to your app or website, including video previews, trending videos, and other useful metadata.


Quickly and reliably define the slices of the web that you want to draw from. Change the parameters of the sites you want and don't want at any time. Explore site suggestions to intelligently expand the scope of your search domain.


Labs provides developers with an early look at emerging Cognitive Services technologies. Early adopters who do not need market-ready technology can discover, try and provide feedback on new Cognitive Services technologies before they are generally available.


Calculate route logistics with deeper location intelligence to account for enterprise requirements, like weight, height, and hazardous materials.


Calculate isochrones - time and distance-based recommendations for enterprise route optimization.


Score the attractiveness of a location, based on how many of a particular amenity are within a specific distance.


Create distance matrices, enabling you to calculate a histogram of travel times, and serve as stepping stone for enterprise route optimization.


Find events associated with Wikipedia entities. Begin with a Wikipedia entity, and receive a list of related events organized by time.


Incorporate gesture-based controls into your apps. Quickly define and implement customized hand gestures, creating a more natural user experience.


Free, interactive coding in the browser, powered by Jupyter Notebooks.

The book introduces the core libraries essential for working with data in Python: particularly IPython, NumPy, Pandas, Matplotlib, Scikit-Learn, and related packages. Familiarity with Python as a language is assumed.

Get a brief introduction to charting and graphing capabilities of R in the Jupyter notebook. You will learn how to make line charts, pie charts, and scatter plots.

Get a brief introduction to using F# in Jupyter Notebooks.

Notebooks can allow anyone with a social media account to gain a greater understanding about customers and communities by analyzing social feeds.

Learn the basics of Python 3 in Azure Notebooks. Learn Python syntax, standard data types, as well as how to write a simple program.

There are many ways to fetch your data within a Jupyter notebook. This sample aims to show you a few different ways of doing so.

A core course in language fundamentals, data analysis, and machine learning from Microsoft's data scientists. Learn how to write basic programs in Python.

Businesses are interested in predicting problems in advance so that they can proactively prevent them from impacting production and customers. This sample implements a predictive model for component failure.

Unlock the power in your data by training intelligent apps and services using Azure ML. This sample notebook uses research data to train a model to predict body temperatures of mammals in Wisconsin.

These Jupyter notebooks provide a self-study introduction to computing with Python. They have been developed for the computing course in Part IA (Michaelmas Term) of the Engineering Tripos at University of Cambridge. This is a first computing course for undergraduate students.


Python is fully supported in Visual Studio Code through extensions. Popular extensions in the Marketplace provide code completion, linting, debugging, code formatting, snippets, and more.



Learning Resources