News for hackers. Stuff that matters.

A comment on Multi-Task Learning in Atari Video Games with Emergent Tangled Program Graphs. Parent comment

Re:Multi-Task Learning in Atari Video Games with Emergent Ta... by aqsalose on Tuesday July 18, 2017 @03:26AM (#14794850)
They are comparing their genetic programming results with a deep learning paper published in 2015. [1]

[1] https://www.nature.com/nature/journal/v518/n7540/abs/nature1...

[ Parent | on HN ]
Re:Multi-Task Learning in Atari Video Games with Emergent Ta... by phoe-krk on Tuesday July 18, 2017 @03:58AM (#14794975)
What a time to live in, when papers from 2015 are "really old" in 2017.
[ Parent | on HN ]
Re:Multi-Task Learning in Atari Video Games with Emergent Ta... by baq on Tuesday July 18, 2017 @05:04AM (#14795207)
1 deep learning year is about 49 dog years.
[ Parent | on HN ]
Re:Multi-Task Learning in Atari Video Games with Emergent Ta... by amelius on Tuesday July 18, 2017 @04:19AM (#14795053)
It highly depends on the field you're in though.
[ Parent | on HN ]
Re:Multi-Task Learning in Atari Video Games with Emergent Ta... by posterboy on Tuesday July 18, 2017 @06:00AM (#14795397)
What is "exponential growth"!
[ Parent | on HN ]
Re:Multi-Task Learning in Atari Video Games with Emergent Ta... by sk0g on Tuesday July 18, 2017 @08:28AM (#14795959)
It's more logarithmic, isn't it? Right now we're at the beginning stage, where there's massive discoveries and changes happening, but in say, 50 years time, there won't be much changing year-to-year.
[ Parent | on HN ]
Re:Multi-Task Learning in Atari Video Games with Emergent Ta... by jcranberry on Tuesday July 18, 2017 @10:00AM (#14796524)
Logarithmic or logistic?
[ Parent | on HN ]