Home  Trees  Indices  Help 





Kording2004 This implements the Kording2004 cost using a dynamicly tracked mean, but not a dynamically tracked variance. 





















_logger = logging.getLogger('kording2004')

Imports: numpy, theano, mean, ExponentialMean, logging

Return the sum of the squares of all terms in the covariance of [normalizedandcentered] z :param hint: either 'tall' or 'fat' to indicate whether the computation should be carried out on the gram matrix or in the covariance matrix. :note: This is computed using either the inner or outerproduct depending on the `hint` 
Return the sum of the squares of the offdiagonal terms of an uncentered covariance matrix :param z: a matrix of feature responses. Each row is the responses at one timestep. These features must have marginal mean 0 and variance 1 for this cost to make sense as a training criterion. :note: This is computed using the gram matrix, not the covariance matrix 
Return the average squared difference between each feature response and its previous response. :param z: a 3tensor of feature responses. Indexed [sequence][frame][feature] These features must have marginal mean 0 and variance 1 for this cost to make sense as a training criterion. 
Home  Trees  Indices  Help 


Generated by Epydoc 3.0.1 on Thu Mar 18 15:48:16 2010  http://epydoc.sourceforge.net 