Re:Perovskite Neural Trees
by andbberger on Friday May 08, 2020 @02:39PM
(#23117996)
There is a huge advantage to 'embedded computing' (using the physics of your system itself to do the compute): energy efficiency.
[ Parent
| on HN ]
Re:Perovskite Neural Trees
by economicslol on Friday May 08, 2020 @02:43PM
(#23118040)
Possibly, but I didn't see anything in the paper about energy efficiency vs a similar software implementation of their neural net and I don't think the wider Deep Learning community really has spent much time thinking about energy efficiency of their models.
Re:Perovskite Neural Trees
by andbberger on Friday May 08, 2020 @03:20PM
(#23118396)
There is a substantial subfield doing embedded deep learning - they absolutely care about energy efficiency.
Re:Perovskite Neural Trees
by economicslol on Monday May 11, 2020 @04:26PM
(#23146597)
"Substantial", maybe. I don't recall any major papers this year about efficiency in NeurIPS, ICLR, etc.
Nevertheless I think my point on "the wider Deep Learning community" not focusing on efficiency is correct.