Neural networks, linear functions and neglected nonlinearity (Q2386624)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Neural networks, linear functions and neglected nonlinearity |
scientific article |
Statements
Neural networks, linear functions and neglected nonlinearity (English)
0 references
25 August 2005
0 references
The article focuses on the ability of feedforward networks to approximate a linear function. By means of MAPLE empirical experiments one justifies the following statement: neural networks can represent linear functions without the need for skip-layer connections. In case skip-layer formulation is used, there are potential problems in separating linear and nonlinear components. Statistical tests with neural networks make use of these issues.
0 references
universal approximation
0 references
skip-layer connections
0 references
feedforward neural networks
0 references