Inception Network Predicts Triple Intersection Numbers
This study uses an Inception convolutional neural network to predict triple intersection numbers of Calabi-Yau threefolds, reporting about 90% accuracy under standard fivefold cross-validation. The work moves beyond prior Hodge-number predictions by targeting intersection-theoretic invariants, a finer topological descriptor relevant to string compactifications. The results indicate that machine learning can learn refined algebraic-geometric invariants, potentially accelerating classification and computation in algebraic geometry.
Key Points
- 1Achieves ~90% accuracy predicting triple intersection numbers using an Inception CNN with fivefold cross-validation
- 2Demonstrates that intersection-theoretic invariants are learnable, extending beyond earlier Hodge-number prediction efforts
- 3Enables data-driven classification of Calabi-Yau topologies and accelerates computational algebraic geometry workflows
Scoring Rationale
Extends ML to refined topological invariants with practical utility, limited by single-dataset focus and unclear peer-review.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
