One model to learn them all | the morning paper


19 bookmarks. First posted by skchrko 9 days ago.


One model to learn them all Kaiser et al., arXiv 2017 You almost certainly have an abstract conception of a banana in your head. Suppose you ask me if I’d like anything to eat. I can say the word ‘banana’ (such that you hear it spoken), send you a text message whereby you see (and…
architecture  machine  learning  deeplearning 
6 days ago by e2b
One model to learn them all Kaiser et al., arXiv 2017 You almost certainly have an abstract conception of a banana in your head. Suppose you ask me if I’d like…
from instapaper
8 days ago by hiroprot
We’d need to be able to support different input and output modalities (as required by the task in hand), we’d need a common representation of the learned knowledge that was shared across all of these modalities, and we’d need sufficient ‘apparatus’ such that tasks which need a particular capability (e.g. attention) are able to exploit it. ‘One model to rule them all’ introduces a MultiModel architecture with exactly these features, and it performs impressively we
ai  Architecture 
8 days ago by janpeuker
Learn multiple modalities at once.
machine  Learning 
8 days ago by traggett
Favorite tweet: tek_news

HNews: One model to learn them all https://t.co/VMZkLnkedH

— Tech news (BOT) (@tek_news) January 12, 2018

http://twitter.com/tek_news/status/951963276199514112
IFTTT  twitter  favorite 
8 days ago by tswaterman
You almost certainly have an abstract conception of a banana in your head. Suppose you ask me if I’d like anything to eat. via Pocket
Pocket 
9 days ago by LaptopHeaven
You almost certainly have an abstract conception of a banana in your head. Suppose you ask me if I’d like anything to eat. via Pocket
IFTTT  Pocket 
9 days ago by archizoo
"One model to learn them all" Kaiser et. al, 2017

A single model that cop…
themorningpaper  from twitter_favs
9 days ago by skchrko