Microsoft Cognitive Services - powerful algorithms to build custom apps with just a few lines of code

Microsoft Cognitive Services is a collection of the following APIs:

1. Academic Knowledge API  helps to interpret user queries for academic intent and retrieve rich information from the Microsoft Academic Graph (MAG). The MAG knowledge base is a web-scale heterogeneous entity graph comprised of entities that model scholarly activities: field of study, author, institution, paper, venue, and event. The MAG data is mined from the Bing web index as well as an in-house knowledge base from Bing.
2. Bing Autosuggest API lets partners send a partial search query to Bing and get back a list of suggested queries that other users have searched on 
3. Bing Image Search API provides a similar (but not exact) experience to Bing.com/Images 
4. Bing News Search API provides a similar (but not exact) experience to Bing.com/News 
5. Bing Speech API is a cloud-based API that provides advanced algorithms to process spoken language. With this API, developers can add speech driven actions to their applications including real-time interaction with the user. This REST API offers industry-leading speech-to-text, text-to-speech, and language understanding capabilities delivered through the cloud. Microsoft has used Bing Speech API for Windows applications like Cortana and Skype Translator as well as Android applications like Bing Torque for Android Wear and Android Phone.
6. Bing Spell Check API which performs contextual spell checking for any text and provides inline suggestions for misspelled words. Current spell-checkers rely on verifying spelling and grammar against dictionary-based rule sets which get updated and expanded periodically. In contrast, the Bing team has developed a web-based spell-checker that leverages machine learning and statistical machine translation to dynamically train a constantly-evolving and highly-contextual algorithm to provide spell checking on-demand for almost any word or phrase that exists on the web.
7. Bing Video Search API provides a similar (but not exact) experience to Bing.com/Videos 
8. Bing Web Search API provides a similar (but not exact) experience to Bing.com/Search 
9. Microsoft Computer Vision API is a cloud-based API that provides developers with access to advanced algorithms for processing images and returning information. By uploading an image or specifying an image URL, Microsoft Computer Vision algorithms can analyze visual content in different ways based on inputs and user choices. Computer Vision API offers image “tagging” based on more than 2000 recognizable objects, living beings and actions. In cases where tags may be ambiguous or not common knowledge, the API response provides “hints” to clarify the meaning of the tag in context of a known setting. 
10. Microsoft Emotion API allows you to build more personalized apps with Microsoft’s cloud-based emotion recognition algorithm. The Emotion API takes 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, from the Face API. The emotions detected are happiness, sadness, surprise, anger, fear, contempt, disgust or neutral. 
11. Microsoft Entity Linking Intelligence Service is a web service created to help developers with tasks relating to entity linking.Sometimes in different contexts, a word might be used as a named entity, a verb, or other word form within a given sentence. For example, in the case where “times” is a named entity, it still may refer to two separately distinguishable entities, such as “The New York Times” or “Times Square”. Given a specific paragraph within a document, the Entity Linking Intelligence Service will recognize and identify each separate entity based on its context. 
12. Microsoft Face API is a cloud-based API that provides the most advanced algorithms for face detection and recognition. The Face API provides high precision face location detection that can detect up to 64 human faces in an image. Face detection can be done by uploading an entire JPEG file or by specifying a URL of an existing JPEG image on the web.
13. Microsoft Knowledge Exploration Service (KES) offers a fast and effective way to add interactive search and refinement to applications. With KES, you can build a compressed index from structured data, author a grammar that interprets natural language queries, and provide interactive query formulation with auto-completion suggestions.
14. Linguistic Analysis APIs provide access to natural langauge processing (NLP) tools that identify the structure of text. The current release provides three types of analysis: Sentence separation and tokenization, Part-of-speech tagging, Constituency parsing
15. Language Understanding Intelligent Services (LUIS) is designed to enable you to quickly deploy an HTTP endpoint that will take the sentences you send it and interpret them in terms of the intention they convey and the key entities that are present. One of the key problems in human-computer interactions is the ability of the computer to understand what a person wants, and to find the pieces of information that are relevant to their intent. Once your application is deployed and traffic starts to flow into the system, LUIS uses active learning to improve itself.
16. The Recommendations API built with Microsoft Azure Machine Learning helps your customer discover items in your catalog. Customer activity in your digital store is used to recommend items and to improve conversion in your digital store. The recommendation engine may be trained by uploading data about past customer activity or by collecting data directly from your digital store. When the customer returns to your store you will be able to feature recommended items from your catalog that may increase your conversion rate.
17. Microsoft Speaker Recognition APIs are cloud-based APIs that provide the most advanced algorithms for speaker verification and speaker identification.
18. Text Analytics API is a suite of text analytics services built with Azure Machine Learning currently offering APIs for sentiment analysis, key phrase extraction and topic detection for English text, as well as language detection for 120 languages
19. Microsoft Video API is a cloud-based API that provides advanced algorithms for tracking faces, detecting motion, stabilizing and creating thumbnails from video.
20. Microsoft Web Language Model API (WebLM) is a REST-based cloud service providing state-of-the-art tools for natural language processing. Using this API, your application can leverage the power of big data through language models trained on web-scale corpora collected by Bing in the EN-US market. 

The following Bing APIs are generally available: Bing Autosuggest API, Bing Spell Check API, Bing Search APIs. These Bing APIs are available as standalone services, and general availability pricing went into effect on July 1, 2016.

This Week I Learned - Week #167

This Week I Learned -

* A web page I built with StupidTable jQuery plugin to sort a table was about three times lighter than the more feature-rich DataTables jQuery plugin

* Nice code sample of an Azure Function that uses a blob trigger, sends the uploaded object to be analysed by Cortana Intelligence and stores the results in a DocumentDB collection.

* It is possible to get data (from a relational database) into and out of a Google Sheet programmatically

* Windows App Studio which makes is easy to build a Windows Phone app without coding now provides a REST API Data Source feature that allows users to integrate apps with third party APIs.

* Power BI is an evolution of the add-ins previously available in Excel: Power Pivot, Power Query, and Power View. You can use Power BI with or without Excel—you no longer are dependent on the version of Microsoft Office installed at your company. Power BI is not just a tool: it is an ecosystem that can integrate existing corporate BI with Self-Service BI - from the Intro of the free ebook Introducing Microsoft Power BI [PDF]

* Downloading MeasureUp practice tests to virtual machines is prohibited.

* Microsoft beat Apple to buy PowerPoint for $14 million (in cash) in 1987, its first significant acquisition. Robert Gaskins helped invent PowerPoint at Forethought Inc. in 1984. After the sale Robert reported directly to Bill Gates, heading up Microsoft’s business unit in Silicon Valley. He managed the growth of PowerPoint to $100 million in annual sales before his retirement in 1993.

* Kaggle hosts competitions provided by industry and academia to find machine learning solutions on different data sets. It also hosts publicly available datasets like the Enron email dataset (354.72 MB) which contains approximately 500,000 emails generated by employees of the Enron Corporation. It was obtained by the Federal Energy Regulatory Commission during its investigation of Enron's collapse.

* Active noise canceling actually uses a mic to listen to ambient noise and then plays the inverse sound wave into the headset, "canceling" the ambient noise

* How drivers of cab aggregation services game the system to create artificial scarcity and trigger surge pricing - drivers concentrate in one location, switch off their app, and create artificial scarcity. They use the second phones to keep track on the rising prices. Once the surge begins, they log back again.

* Locally grown food products are becoming more desirable than products sourced from far away...free-range livestock that are fed natural foods may be more desirable than cage-raised livestock that are fed a processed food

* Food Safety and Standards Authority of India (FSSAI) Chief Executive Officer Pawan Agarwal is tasked with improving food testing facilities and working with food businesses to improve manufacturing practices and hygiene standards. He feels it is wrong for Indians to expect international food safety standards as it is impractical

* If you file your return on time, losses of this year can be set-off against gain of forthcoming years. Supreme Court of India rejected a petition of Ms. J Jayalalitha, Chief Minister of the state of Tamil Nadu against Madras High Court order to prosecute her for non filing of return of a firm in which she was a partner.

* A total of 28.7 million individuals filed income tax returns, of which 16.2 million did not pay any tax, leaving only about 12.5 million tax-paying individuals, which is just about 1 percent of the 1.23 billion population of India in the year 2013.  The Prime Minister of India urged tax officials — who are responsible for providing Rs 17 lakh crore to the government — to double the number of taxpayers to 10 crore from 5.43 crore (54.3 million) now. Google throws up 7 crore search results in response to the question 'How to pay tax in India' and 12 crore answers for 'How not to pay tax in India'.

* Labrador retriever is the most popular dog according to American Kennel Club which publishes an annual list of the most popular dog breeds in the United States, based on registration data for the nearly 200 breeds they officially recognize - WSJ