News for hackers. Stuff that matters.

A comment on Deep Learning – The “Why” Question (2018). Parent comment

Re:Deep Learning – The “Why” Question (2018) by nl on Sunday June 28, 2020 @11:25AM (#23669360)
This isn't correct.

No amount of compute power will let a RNN/LSTM outperform a Transformer.

No amount of compute power will let an AlexNet or Inception style network train as well as a ResNet.

[ Parent | on HN ]
Re:Deep Learning – The “Why” Question (2018) by anukriti on Monday June 29, 2020 @12:38PM (#23679156)
> I think the fact that we're seeing so much progress in deep learning without any theoretical basis

I don't understand what you mean by this? Any neural network is first build in theory and then tried out practically by coding and testing. I think practitioner and scientist play equal role.

[ Parent | on HN ]