Fix typo in README

This commit is contained in:
Mattéo Delabre 2019-12-18 11:26:57 -05:00
parent 6921be6ca6
commit 73d2572fbe
Signed by: matteo
GPG Key ID: AE3FBD02DC583ABB
1 changed files with 1 additions and 1 deletions

View File

@ -23,7 +23,7 @@ The ConstellationNet model is defined inside the `constellation/` folder. At the
`experiment.py` runs experiments to find the best hyperparameters for each constellation order. Currently, the following parameters are tested: `experiment.py` runs experiments to find the best hyperparameters for each constellation order. Currently, the following parameters are tested:
* `order`, the number of points in the constellation, is 4, 16 or 32. * `order`, the number of points in the constellation, is 4, 16 or 32.
* `initial_learning_rate`, the first learning rate used by the optimizer, is $10^-2$, $10^-1$ or $1$. * `initial_learning_rate`, the first learning rate used by the optimizer, is $10^{-2}$, $10^{-1}$ or $1$.
* `batch_size`, the number of training examples in each batch, expressed as a multiple of `order`, is 8 or 2048. * `batch_size`, the number of training examples in each batch, expressed as a multiple of `order`, is 8 or 2048.
* `first_layer`, the size of the first hidden layer, ranges from 0 to the constellations order in steps of 4 (0 meaning that there is no hidden layer). * `first_layer`, the size of the first hidden layer, ranges from 0 to the constellations order in steps of 4 (0 meaning that there is no hidden layer).
* `last_layer`, the size of the second hidden layer, ranges from 0 to `first_layer` (because the second layer is never larger than the first). * `last_layer`, the size of the second hidden layer, ranges from 0 to `first_layer` (because the second layer is never larger than the first).