| Parameters | Description | Value |
|---|---|---|
| LSTM layers | - | 2 |
| LSTM Nodes | - | 33 |
| Dense Nodes | - | 95 |
| Dense Activation | - | selu |
| Normalisation window | - | 1000 |
| Batch size | Number of sequence in a batch | 150 |
| Sequence length | Number of previous points to take into account | 22 |
| News lag | Number of days prior to current day to take news into account | 1 |
| News confidence | Only news classified above this confidence value gets used | 75% |
| Learning rate | Cyclic, initial value | 0.0005 |
| Dropout | % of nodes that get dropped after each iteration | 33 |
Last active
August 15, 2019 15:45
-
-
Save jwsmithers/d4932ff585239f5d781a536fca58b449 to your computer and use it in GitHub Desktop.
HyperparameterTable
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment