Neural networks are becoming increasingly popular in data analysis, not only for experimental data but also for constructing simplified models and predictions out of complex theories. I am interested in the application of neural networks in physical problems and data analysis.
In my Bachelor thesis I trained a neural network with the goal of recognizing magnetic structures. I started off by analyzing and calculating the phase transition for the 2D Ising model with a Monte Carlo simulation. With our simulation we generated data close to the critical point with areas of different coupling constants. This data was then used to train a neural network on recognizing areas of different coupling constants in our system.
During the course of my Master Studies I will focus more on the applications of neural networks on magnetic- and other topological structures.