AI RESEARCH
A Complete Symmetry Classification of Shallow ReLU Networks
arXiv CS.LG
•
ArXi:2604.14037v1 Announce Type: new Parameter space is not function space for neural network architectures. This fact, investigated as early as the 1990s under terms such as ``reverse engineering," or ``parameter identifiability", has led to the natural question of parameter space symmetries\textemdash the study of distinct parameters in neural architectures which realize the same function.