A Comparison of Selected Optimization Methods for Neural Networks
Which numerical methods are ideal for training a neural network? In this report four different optimization methods are analysed and compared to each other. First, the most basic method Stochastic Gradient Descent that steps in the negative gradients direction. We continue with a slightly more advan...
| Main Authors: | , |
|---|---|
| Format: | Others |
| Language: | English |
| Published: |
KTH, Skolan för teknikvetenskap (SCI)
2020
|
| Subjects: | |
| Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-276231 |