Refind
VentureBeat

Key takeaways from DeepMind aims to marry deep learning and classic algorithms

If successful, DeepMind's goal to bridge deep learning and classical computer science could revolutionize AI and software as we know them. Open at source

221
Reader View
Made me smarter
Read later
Edit
Most highlighted
This is what DeepMind is working on, and its success is important to the eventual uptake of neural networks in wider commercial applications.
Algorithms are comprised of a fixed set of rules that are executed on some input, and usually good algorithms have well-known properties.
What Blundell and Veličković are trying to do is get somewhere in between those two extremes, where you have something that’s a bit more structured but still fits the data, and doesn’t necessarily require a human in the loop
Your notes & highlights

  Save highlights in Reader View or with our Chrome extension.

This your link? Claim it

Made for busy people.
About RefindDeep DivesTopicsHashtagsHelpLegal
CreatorsCuratorsDevelopersPublishersSponsorsEducation
© 2021 Refind Inc.
Apple App StoreGoogle Play StoreChrome Web Store