The dynamics of hebbian synapses can be stabilized by a nonlinear decay term.
Helmut RiedelDetlev SchildPublished in: Neural Networks (1992)
Keyphrases
- hebbian learning
- highly nonlinear
- associative memory
- nonlinear dynamics
- continuous stirred tank reactor
- neural network
- power law
- synaptic weights
- complementarity problems
- biologically inspired
- dynamic model
- dynamical systems
- high dimensional
- learning rules
- receptive fields
- nonlinear functions
- fuzzy cognitive maps
- network model
- tracking error
- external disturbances
- information retrieval