Stefano Lanza - Neural Network Learning and Quantum Gravity

The landscape of low-energy effective field theories stemming from string theory is too vast for a systematic exploration. However, the meadows of the string landscape may be fertile ground for the application of machine learning techniques. In this talk, I will illustrate that Quantum Gravity effective field theories are naturally endowed with key statistical learnability properties due to their underlying tame structures. Consequently, several problems therein formulated can be concretely addressed with machine learning techniques, delivering results with sufficiently high accuracy.