Deep Network With Approximation Error Being Reciprocal of Width to Power of Square Root of Depth
A new network with super-approximation power is introduced. This network is built with Floor (⌊x⌋) or ReLU (max{0,x}) activation function in each neuron; hence, we call such networks Floor-ReLU networks. For any hyperparameters N∈N+ and L∈N+, we show that Floor-ReLU networks with width max{d,5N+13}...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
NLM (Medline)
2021
|
Subjects: | |
Online Access: | View Fulltext in Publisher |