Abstract
An algorithm for the minimum vertex cover problem based on HNN leaning is presented. The network phase performs gradient descent in state domain, and finds a set of states minimizing the HNN's energy. When the HNN gets stuck, the learning phase is performed to fill up the local minimum valley by modifying parameter in gradient ascent direction of the energy.
Original language | English |
---|---|
Pages | 1829-1834 |
Number of pages | 6 |
State | Published - 2004 |
Event | SICE Annual Conference 2004 - Sapporo, Japan Duration: 2004/08/04 → 2004/08/06 |
Conference
Conference | SICE Annual Conference 2004 |
---|---|
Country/Territory | Japan |
City | Sapporo |
Period | 2004/08/04 → 2004/08/06 |
Keywords
- Gradient ascent learning
- Hopfield neural network
- Local minimum
- Vertex cover
ASJC Scopus subject areas
- Control and Systems Engineering
- Computer Science Applications
- Electrical and Electronic Engineering