Recent progress on NNPDF for LHC

We present recent results of the NNPDF collaboration on a full DIS analysis of Parton Distribution Functions (PDFs). Our method is based on the idea of combining a Monte Carlo sampling of the probability measure in the space of PDFs with the use of neural networks as unbiased universal interpolating functions. The general structure of the project and the features of the fit are described and compared to those of the traditional approaches.