The Representations of Deep Neural Networks Trained on Dihedral Group Multiplication
Gavin McCracken ⋅ Sihui Wei ⋅ Gabriela Moisescu-Pareja ⋅ Harley Wiltzer ⋅ Jonathan Love
Abstract
We find coset and approximate coset circuits play a key role in how multilayer perceptrons learn dihedral group multiplication, consistent with recent findings on modular addition.
Chat is not available.
Successful Page Load