The performance of the kernel-based learning algorithms, such as support vector domain description, depends heavily on the proper choice of the kernel parameter. It is desirable for the kernel machines to work on the optimal kernel parameter that adapts well to the input data and the pattern classification tasks. In this paper we present a novel algorithm to optimize the Gaussian kernel parameter by maximizing a classical class separability criterion, and the problem is solved through a steepest descent algorithm, Simulation results on six benchmark datasets have successfully validated the effectiveness of the proposed method.