A case where a spindly two-layer linear network decisively outperforms any neural network with a fully connected input layer
[ 1 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ P ] employee
2021
chapter in monograph / paper
english
- neural networks
- scale invariance
- spindly network
- gradient descent
- lower bounds
1214 - 1236
publisher's website
final published version
at the time of publication
5
70