A Lagrangian Approach to Fixed Points

Part of Advances in Neural Information Processing Systems 3 (NIPS 1990)

Bibtex Metadata Paper


Eric Mjolsness, Willard Miranker


We present a new way to derive dissipative, optimizing dynamics from the Lagrangian formulation of mechanics. It can be used to obtain both standard and novel neural net dynamics for optimization problems. To demonstrate this we derive standard descent dynamics as well as nonstan(cid:173) dard variants that introduce a computational attention mechanism.