Normal prob. density function (pdf) with arbitrary covariance matrix. Evaluate the multi-variate density with mean vector m and covariance matrix C for the input vector xs. Assumes that the N datapoints are d dimensional. Then m is dx1 or 1xd, C is dxd, and xs is dxN or NxD where N is the number of samples to be evaluated. INPUTS xs - points to evaluated (Nxd or dxN) m - mean vector (dx1 or 1xd) C - Covariance matrix (dxd) OUTPUTS ps - probability density at each x DATESTAMP 29-Sep-2005 2:00pm