Differences

This shows you the differences between two versions of the page.

--- data_mining:neural_network:transfer_learning [2018/05/25 23:11] – [Transfer learning] phreazer
+++ data_mining:neural_network:transfer_learning [2018/05/25 23:13] (current) – [Transfer learning] phreazer
@@ Line 17: / Line 17: @@
 Another trick:
-  * Precompute output of frozen layer for all samples (save computation time later)
+  * Precompute output of frozen layers for all samples (save computation time later)
+For larger set of samples:
+  * Only freeze first layers, train last few layers (and replace softmax)
+For large set of samples:
+  * Use weights as initialization, then train (and replace softmax)
 ===== Image-based NNs =====