Recursive nonlinear system identification by a stochastic gradient algorithm: stability, performance, and model nonlinearity considerations.
David LevanonyNadav BermanPublished in: IEEE Trans. Signal Process. (2004)
Keyphrases
- stochastic gradient
- probabilistic model
- objective function
- cost function
- learning algorithm
- optimal solution
- worst case
- em algorithm
- similarity measure
- parameter estimation
- kalman filter
- np hard
- particle swarm optimization
- convergence rate
- bayesian framework
- exponentiated gradient
- utility maximization
- average case
- expectation maximization
- knn
- face recognition