ResNet with one-neuron hidden layers is a Universal Approximator
Hongzhou Lin, Stefanie Jegelka
–Neural Information Processing Systems
This stands in sharp contrast to fully connected networks, which are not universal approximators if their width is the input dimensiond[21,11].
Neural Information Processing Systems
Feb-12-2026, 03:18:35 GMT
- Country:
- North America
- Canada > Quebec
- Montreal (0.04)
- United States > Massachusetts
- Middlesex County > Cambridge (0.05)
- Canada > Quebec
- North America
- Technology: