Deep Neural Nets with Interpolating Function as Output Activation
Bao Wang, Xiyang Luo, Zhen Li, Wei Zhu, Zuoqiang Shi, Stanley Osher
–Neural Information Processing Systems
And we propose end-to-end training and testing algorithms for this new architecture. Compared to classical neural nets with softmax function as output activation, the surrogate with interpolating function as output activation combines advantages of both deep and manifold learning.
Neural Information Processing Systems
Nov-17-2025, 22:53:51 GMT
- Country:
- Asia > China
- Hong Kong (0.04)
- North America
- Canada > Quebec
- Montreal (0.04)
- United States > California
- Los Angeles County > Los Angeles (0.14)
- Canada > Quebec
- Asia > China
- Industry:
- Technology: