Visual scenes are often comprised of sets of independent objects. Yet, current vision models make no assumptions about the nature of the pictures they look at.

Yannic Kilcher explore a paper on object-centric learning.

By imposing an objectness prior, this paper a module that is able to recognize permutation-invariant sets of objects from pixels in both supervised and unsupervised settings. It does so by introducing a slot attention module that combines an attention mechanism with dynamic routing.

Content index:

  • 0:00 – Intro & Overview
  • 1:40 – Problem Formulation
  • 4:30 – Slot Attention Architecture
  • 13:30 – Slot Attention Algorithm
  • 21:30 – Iterative Routing Visualization
  • 29:15 – Experiments
  • 36:20 – Inference Time Flexibility
  • 38:35 – Broader Impact Statement
  • 42:05 – Conclusion & Comments

Microsoft Mechanics has SQL Server guru and recent Data Driven guest, Bob Ward on to talk about Azure Migrate.

Running SQL Server on-premises and looking to move to Azure? Review your best options for assessment and migration. Bob Ward, SQL Server database expert and engineering lead, joins host Jeremy Chapman to walk through different migration options for moving your SQL Databases into the cloud, and then shows how to perform a migration end-to-end.

If you’re a regular visitor to this blog, then you know that the use of machine learning and AI technologies rapidly on the rise and has been for a while now. This growth mirrors the increasing use of cloud service environments to leverage mass-scale computing resources.

Large cloud service providers offer ready-made machine learning and AI capabilities, models, and tools that make it easier than ever to build more intelligent applications and data mining scenarios.

But what does this mean for privacy?

Of course, this is a concern for security and privacy professionals that must be addressed. Mining data with machine learning and AI requires staggering quantities of data, and some of that data is bound to be sensitive in nature. On top of this, increasing numbers of regulations mandate data privacy measures for cloud services, making privacy-preserving machine learning techniques all the more critical.

Microsoft Mechanics shows us a practical use case for Predictive Maintenance, Safety, and Efficiency through Microsoft Azure Synapse.

Find out how Azure Synapse is part of the next-generation data and analytics platform for global aviation tech company, GE Aviation. Jeremy Chapman speaks with Luke Bowman, Senior Product Manager at GE Aviation’s Digital Group, to discuss how they are evaluating Azure Synapse to drive the development of predictive maintenance analytics at scale to help airlines, as well as to get ahead of issues to optimize flight safety and operational efficiency.

If you are new to Azure Synapse, it’s Microsoft’s limitless analytics platform that brings enterprise data warehousing and big data processing together into a single service, removing the traditional constraints for analyzing data of all shapes and sizes.