AI Research
On the growth of the parameters of approximating ReLU neural networks
An analysis of parameter growth in fully connected ReLU networks approximating smooth functions
This work focuses on the analysis of fully connected feed forward ReLU neural networks as they approximate a given, smooth function.
AC
ArXiv CS.LG
Source
ArXiv CS.LG
AI Analysis
Generated insight by OnAirToday AI
Understanding how network parameters grow during approximation can clarify the resources needed to represent smooth functions with ReLU networks. This analysis focuses attention on model size as well as approximation itself.
Powered by AI • Not a substitute for human analysisMore Insights →
Share
Filed under:AI Research
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.