An AI Perspective on Phenomenology and Strings
Date:
Particle physics and cosmology are fascinating topics both from an experimental point of view and a theoretical perspective. The balance between theoretical predictions and physical evidence is however delicate and usually requires contributions from several research areas. In the effort to find a unified description of fundamental forces of nature, the framework of String Theory provides some of the needed tools. We present how hints of experimental evidence of particle physics might be recovered using different mathematical models, and how cosmological singularities such as the Big Bang can find some explanations inside a string theory.
On this line, we present a new approach to extract phenomenological information based on Artificial Intelligence techniques. We introduce a deep learning model based on the Inception neural network capable of predicting the Hodge numbers of Calabi-Yau 3-folds, which are necessary objects for the consistency of the theory. Using methods inspired by Google’s research in computer vision and object detection tasks, we recover information of phenomenological relevance with near-perfect accuracy. We thus prove that the introduction of convolutional networks and AI methodologies, used in research as well as in the industry, can dramatically improve the generalisation properties of the models, opening even more reliable possibilities to the application of such methods to physical data coming both from theory and experiments.