Meta’s ‘data2vec’ is a step toward One Neural Network to Rule Them All

Metas data2vec is a step toward One Neural Network to Rule Them All

Ambidextrous networks are racking up scores on benchmark tests of AI. The latest addition is what’s called “data2vec,” developed by researchers at the AI division of Meta (parent of Facebook, Instagram, and WhatsApp).

Meta researcher Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu, and Michael Auli reveal in a blog post, is to approach something more like the general learning ability that the human mind seems to encompass.

The name data2vec is a play on the name of a program for language “embedding” developed at Google in 2013 called “word2vec.” That program predicted how words cluster together, and so word2vec is representative of a neural network designed for a specific type of data, in that case text. 

Read More: Zdnet

Check Out The New Enterprisetalk Podcast. For more such updates follow us on Google News Enterprisetalk News.

Previous articleGoogle calls for a secure ‘data transfer framework’ between the US and EU
Next articleBrivo Appoints Ingo Meijer to Lead the Company’s European Expansion