Hyperparameter search space table.

<p>The best set of parameters is {number of conv filters, <i>N</i>_<i>c</i>: 256, number of units in LSTM <i>N</i>_<i>h</i>: 64, dropout probability for Dropout Layer: 0, learning rate: 0.001} for read-level prediction on 5-fold cross validation of training data. The window size ... View More