Putting together a demo or a simple proof of concept for your Vision AI at the edge project has become pretty simple. But bringing this project to pilot then to production can be daunting.

Mahesh Yadav joins Olivier on this new episode to introduce the open source project VisionOnEdge which gives you all you need to rapidly get your project to a production ready state.

Learn more reading Mahesh’s blog post at aka.ms/iotshow/VisionOnEdge

Yannic Kilcher covers a paper where Geoffrey Hinton describes GLOM, a Computer Vision model that combines transformers, neural fields, contrastive learning, capsule networks, denoising autoencoders and RNNs.

GLOM decomposes an image into a parse tree of objects and their parts. However, unlike previous systems, the parse tree is constructed dynamically and differently for each input, without changing the underlying neural network. This is done by a multi-step consensus algorithm that runs over different levels of abstraction at each location of an image simultaneously. GLOM is just an idea for now but suggests a radically new approach to AI visual scene understanding.

The Lunar rover has been instrumental in helping us advance our understanding of the Moon and our Universe, and in the new Netflix Original, Over the Moon, it makes an appearance when Fei Fei lands on the moon with her buddy Bungee and brother Chin.

In this video, Dr. G will build an image classifier using Azure Custom Vision to identify Bungee so that the Lunar Rover can capture in-the-moment pictures of Bungee (and not rocks) on the Moon and send them to Fei Fei to keep as memories!

No coding experience required!

PyTorch is one of the most popular open source machine learning framework that accelerates the path from research to production deployment.

In this tutorial, Dmytro Dzhulgakov, core contributor for PyTorch, will go through an introductory level hands-on tutorial for building fashion recognizer.

Related links: