To provide customers with an easier network configuration, all newly created virtual clusters will be enabled for access over global virtual network peering connections, now in general availability.

This enables customers to pair managed instances in failover group configuration, in an easy and performant way, by simply connecting virtual networks in different regions. By utilizing global virtual network peering for your managed instances, you will save time through easy network configuration and offload your gateways from database replication traffic.

Review this new feature and more in this episode with Srdan Bozovic.

Time Index:

  • [00:42] Why Global VNet Peering Support is Important
  • [01:39] Auto-failover group connectivity architecture
  • [03:52] Take advantage of Global VNet Peering Support

Resources:

Yannic Kilcher explains why transformers are ruining convolutions.

This paper, under review at ICLR, shows that given enough data, a standard Transformer can outperform Convolutional Neural Networks in image recognition tasks, which are classically tasks where CNNs excel. In this Video, I explain the architecture of the Vision Transformer (ViT), the reason why it works better and rant about why double-bline peer review is broken.

OUTLINE:

  • 0:00 – Introduction
  • 0:30 – Double-Blind Review is Broken
  • 5:20 – Overview
  • 6:55 – Transformers for Images
  • 10:40 – Vision Transformer Architecture
  • 16:30 – Experimental Results
  • 18:45 – What does the Model Learn?
  • 21:00 – Why Transformers are Ruining Everything
  • 27:45 – Inductive Biases in Transformers
  • 29:05 – Conclusion & Comments

Related resources:

  • Paper (Under Review): https://openreview.net/forum?id=YicbFdNTTy

When you think of “deep learning” you might think of teams of PhDs with petabytes of data and racks of supercomputers.

But it turns out that a year of coding, high school math, a free GPU service, and a few dozen images is enough to create world-class models. fast.ai has made it their mission to make deep learning as accessible as possible.

In this interview fast.ai co-founder Jeremy Howard explains how to use their free software and courses to become an effective deep learning practitioner.

Learn More:

Sabine Hossenfelder explains what differential equations are, go through two simple examples, explain the relevance of initial conditions and how differential equations generally work, and then discuss what this means to the question whether the future is determined already.

Time Index:

  • 0:00 Motivation and Content Summary
  • 0:55 Example Disease Spread
  • 3:25 Example Newton’s Law
  • 5:18 Initial Values
  • 6:15 What are Differential Equations used for?
  • 7:08 How Differential Equations determine the Future