Research on Construction of Recommendation System On account of CNN and PMF model

Abstract

Abstract As an important branch and direction of machine learning, neural network shows its technical superiority in many aspects. However, due to the shortcomings of existing shallow structure algorithms, it is necessary to strengthen the ability to express effects, so as to learn the essential features of data sets from a large number of unlabeled specimens. On account of this, this paper first analyzes the concept and application of CNN network, then studies the algorithm and process of PMF model, and finally gives a recommendation system on account of CNN and PMF model.