NATURAL GRADIENT LEARNING WITH A NONHOLONOMIC CONSTRAINT FOR BLIND DECONVOLUTION OF MULTIPLE CHANNELS

By Shun-ichi AMARIyy, Andrzej CICHOCKIyy, Ruey-wen LIUyyyy. 1999

Subfields: Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

1. Thomas Unterthiner
2. Sepp Hochreiter
3. Kiyotoshi Matsuoka
4. Djork-Arné Clevert
5. Stefano Ermon
6. Dan Hendrycks
7. Kevin Gimpel
8. J. Urgen Schmidhuber

Citations in the corpus

• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) (2015, methodology): “The recently introduced Hessian-Free Optimization technique (Martens, 2010) and the Krylov Subspace Descent methods (Vinyals & Povey, 2012) use an extended Gauss-Newton approximation of the Hessian, therefore they can be interpreted as versions of natural gradient descent (Pascanu & Bengio, 2014).”
• Minimal distortion principle for blind source separation (2002, background): “Next we consider other source signals, which are binary-valued signals generated by a Markov chain given by the following conditional probabilities: { } { } i i i i Pr ( ) = 1| ( 1) 1 = (1 ) / 2, Pr ( ) = 1| ( 1) 1 = (1 ) / 2, s t s t c s t s t c ± − = ± + − = ± − (17) where parameter c takes a…”