Determination of the Edge of Criticality in Echo State Networks Through Fisher Information Maximization.
Lorenzo LiviFilippo Maria BianchiCesare AlippiPublished in: IEEE Trans. Neural Networks Learn. Syst. (2018)
Keyphrases
- fisher information
- echo state networks
- recurrent neural networks
- information geometry
- euclidean space
- probability density function
- positive definite
- multidimensional scaling
- noise level
- model selection
- edge detection
- learning algorithm
- neural network
- geodesic distance
- exponential family
- free energy
- estimation error
- projective transformations
- kullback leibler divergence
- statistical methods
- feature space
- machine learning