We explore the possibilities of using neural networks to study phase transitions. The main question is the level of accuracy which can be accessed in the estimation of the critical point and critical exponents of the statistical physics models. We generate data for two spin models in two dimensions for which analytical solutions exist, the Ising model and Baxter-Wu model. We applied six neural networks with three different architectures to the data and estimated critical temperature and correlation length exponent. We found that accuracy of estimation does depend on the neural network. The critical exponent of Baxter-Wu model estimated by the deep machine learning technique for the first time.