Parameter Continuation with Secant Approximation for Deep Neural Networks
Non-convex optimization of deep neural networks is a well-researched problem. We present a novel application of continuation methods for deep learning optimization that can potentially arrive at a better solution. In our method, we first decompose the original optimization problem into a sequence of...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Others |
| Published: |
Digital WPI
2018
|
| Subjects: | |
| Online Access: | https://digitalcommons.wpi.edu/etd-theses/1256 https://digitalcommons.wpi.edu/cgi/viewcontent.cgi?article=2262&context=etd-theses |