Microsoft Research posted this video of Sumit Gulwani, who founded the PROSE research and engineering team at Microsoft. This team develops programming-by-example (PBE) APIs and ships them through multiple Microsoft products.

PBE is a new frontier in AI wherein the computer programs itself—the user provides input-output examples and the computer synthesizes an intended script. This is significant because 99% of computer users do not know programming. Even for programmers, this can provide a 10-100x productivity increase for many task domains.

A killer application of PBE is in the space of data cleaning/preparation since data scientists often spend up to 80% time wrangling data into a form suitable for learning models or drawing insights. In this video, Sumit illustrates how a data cleaning task, that Python programmers took an average of 30 minutes to finish, can be performed in 30 seconds by non-programmers using the PBE paradigm. In particular, PBE can help ingest a file into tabular format, split a column to extract constituent sub-fields, derive new columns, and suggest form entries.


John Spaith is lead developer on the C SDK for Azure IoT. In the video below, watch him and Olivier Bloch go through the SDK usage and portability for IoT devices running Linux, Windows or real time OSs as well as microcontrollers.

This week James Montemagno is joined by Jim Bennett, a Cloud Developer Advocate at Microsoft, who shows us how to use AI inside a mobile app to identify his daughters’ toys.

In the video below, he walks through using the Azure custom vision service to generate a model to identify different toys, then shows how you can use these models from inside your app, both remotely by calling an Azure service, or locally by running the model on your device using CoreML and Tensorflow.

Show Links: