Computer scientists prove that big neural networks are better
Feb 10, 2022
Wow, this is really interesting.
A new paper says you need more weights in your network to make it more robust! This goes directly against the general wisdom in computational learning theory that lower model complexity (=fewer parameters) lead to more robust models.
QUANTAMAGAZINE.ORG
| Computer Scientists Prove Why Bigger Neural Networks Do Better | Quanta Magazine |
← Back to all articles Quick Navigation: Next:[ j ] – Prev:[ k ] – List:[ l ]