Earlier quoted context omitted.
Thanks! Have you taken a look at the other HN thread I linked to above? In which David answers a similar question here: https://news.ycombinator.com/item?id=18677947 If you have any follow up questions there I will try to get to them!
Its great to see some new way of looking at things in AI. We are also attempting to developing an algorithm which learns without doing a backpropagation more details are http://alpes.ai
A new neural network design could overcome challenges in AI
11–12 of 12 posts
Looking forward to see your results on Imagenet!
Re: A new neural network design could overcome challenges in AI
#12Earlier quoted context omitted.
Does this article do a good job of representing your work?
As with all science communication, it is highly specific to the audience. I would say if you are completely unfamiliar with machine learning then this article accomplishes the job of informing you that we've proposed something exciting and a bit different, and gives some flavour for what kind of problems we're interested in (like continuous time medical data). However, this article assumes essentially zero technical…
Presumably the target audience then is people who got there by accident.
> If your brain hurts (trust me, mine does too), ...
This brings to mind something Ben Goldacre said (sorry can't quote) about the average science journalist being less qualified than the average science article reader.