About this document
Functional Multi Layer Perceptrons Analysis by Tuhma is a document available to read on EtoBox.
This document discusses theoretical properties of functional multi-layer perceptrons (MLP), a natural extension of MLPs to functional inputs. It shows that fundamental results for numerical MLPs, such as universal approximation and consistency, can be extended to the functional MLP model. Functional MLPs are defined using functional neurons that map functional inputs to outputs. Theoretical results demonstrate that functional MLPs are also universal approximators and that optimal parameter estimation is con
- Author
- Tuhma
- Language
- EN