better baseline

2026-06-27 16:44:27 +08:00 · 2019-11-09 08:20:23 +08:00
parent 6546f6687a
commit 6c5004a95b
3 changed files with 706 additions and 702 deletions
@@ -37,11 +37,14 @@ I chose a a difficult example below, it's a window in the test set that deviates

 ![](docs/19.png)

+### Baseline

 Compare this to a quick LSTM baseline below, which didn't predict this divergance from the pattern. (Bear in mind that I didn't tweak this model as much). The uncertainty and prediction are also less smooth and the log probability is lower.

 ![](docs/lstm_with_context.png)

+![](docs/lstm_baseline.png)
+
 ## Code

 This is based on the code listed in the next section, with some changes. The most notable ones add stability, others are to make sure it can handle predicting into the future: