Steepest descent with momentum for quadratic functions is a version of the conjugate gradient method.
Where this comes from
- Record sourced from PubMed, PMID 14690708.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
It is pointed out that the so called momentum method, much used in the neural network literature as an acceleration of the backpropagation method, is a stationary version of the conjugate gradient method. Connections with the continuous optimization method known as heavy ball with friction are also made. In both cases, adaptive (dynamic) choices of the so called learning rate and momentum parameters are obtained using a control Liapunov function analysis of the system.
Medical subject headings
- Neural Networks, Computer
- Nonlinear Dynamics