HN Explorer

Ask HN: Would building synthetic neurons be a breakthrough?

4 points by hsikka ↗ HN
I just finished https://arxiv.org/abs/1705.06963 and was pleasantly surprised at state of neurotrophic computing. Specifically, the use of organic materials to build robust, low power networks that get past the von Neumann bottleneck and allow us to incorporate new levels of sensing into our environment and lives seems extraordinary. TPUs and chips are obviously interesting for orgs like google, but what about synthetic clusters of neurons integrated into our environment? How significant could that be?

2 comments

[ 3.5 ms ] story [ 9.8 ms ] thread
DigiMortality
This looks really interesting. I am going to read this after work!

Comment for visibility

sgillen
I’m not sure it would be as significant as you are thinking. We already have really really cheap low power computing. The von bottleneck is also something people have been working on for a long time, I mean basically the entire memory hieracrchy was invented to get around this bottleneck.

Furthermore I think the biggest problem we have right now is not computing power, but what to do with that power. Even if we suddenly had really cheap low power biological neurons we could wire up today I think it would take humanity a long time to figure out how to do anything really useful with them (in the sense that they perform a task better than a computer would).

But all that said, I think in the longer term alternative and exotic forms of computing will become very useful in the medium to far term future. And having nuerons now to experiment with on a large scale could well lead to be breakthroughs I think we would need to properly utilize that form of computer in the first place!