Image filtering, regardless of whether it is denoising (low pass filtering) or edge detection (high pass filtering) can be considered as a machine learning problem. In fact, filtering is a process of approximation of a desirable result. A filter is considered good, if it approaches this ideal result better than other filters. But any machine learning problem should be considered from exactly the same standpoint. In this paper, we suggest to use a multilayer neural network with multi-valued neurons (MLMVN) as an intelligent image filter. After MLMVN is trained using a number of n x n patches from different images to obtain a clean patch from a noisy one, it can be used as an intelligent filter. It is shown that this filter is robust, since it performs well on different images, which did not participate in the learning process. It terms of PSNR, this approach shows results comparable with other filters commonly recognized as good. A specific advantage of the presented approach is its ability to preserve small details carefully.