Neural networks are not black boxes.
They are rather homeomorphisms.

https://colah.github.io/posts/2014-03-NN-Manifolds-Topology/

https://medium.com/secure-and-private-ai-math-blogging-competition/how-and-why-deep-learning-works-60df8093e19f



On Thu, Feb 11, 2021 at 11:53 PM <[email protected]> wrote:

> Oh maybe those algorithms "backprop" / "SGD" / "simulated annealing" /
> "etc" are just optimizations to make the AI faster? So Markov Models are
> too slow, so we add backprop, at the cost that it is now a blackbox?
> *Artificial General Intelligence List <https://agi.topicbox.com/latest>*
> / AGI / see discussions <https://agi.topicbox.com/groups/agi> +
> participants <https://agi.topicbox.com/groups/agi/members> + delivery
> options <https://agi.topicbox.com/groups/agi/subscription> Permalink
> <https://agi.topicbox.com/groups/agi/Ta86fa089ebd8ca28-M399c7968e0b1c13ad7e4baa0>
>

------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/Ta86fa089ebd8ca28-M6124b2515b3062096e26c071
Delivery options: https://agi.topicbox.com/groups/agi/subscription

Reply via email to