Inception Neural Network for Complete Intersection Calabi-Yau 3-folds
This provides a valuable tool for studying geometric aspects in pure mathematics and string theory, though it is incremental as it applies an existing neural network architecture to a new mathematical problem.
The paper tackled the problem of computing the Hodge number h^{1,1} for complete intersection Calabi-Yau 3-folds using a neural network based on Google's Inception model, achieving 97% accuracy with 30% training data and 99% accuracy with 80% training data.
We introduce a neural network inspired by Google's Inception model to compute the Hodge number $h^{1,1}$ of complete intersection Calabi-Yau (CICY) 3-folds. This architecture improves largely the accuracy of the predictions over existing results, giving already 97% of accuracy with just 30% of the data for training. Moreover, accuracy climbs to 99% when using 80% of the data for training. This proves that neural networks are a valuable resource to study geometric aspects in both pure mathematics and string theory.