AI RESEARCH
A Lower Bound for the Number of Linear Regions of Ternary ReLU Regression Neural Networks
arXiv CS.LG
•
ArXi:2507.16079v2 Announce Type: replace With the advancement of deep learning, reducing computational complexity and memory consumption has become a critical challenge, and ternary neural networks (NNs) that restrict parameters to $\{-1, 0, +1\}$ have attracted attention as a promising approach. While ternary NNs nstrate excellent performance in practical applications such as image recognition and natural language processing, their theoretical understanding remains insufficient.