Table 6 CarboxE site identification using RNN based on LSTM neurons.

From: Computational identification of 4-carboxyglutamate sites to supplement physiological studies using deep learning

Layer type

No. of weights

Embedding layer to convert numeric sequence into vector sequence

\((23 \times 20 = 460)\)

Recurrent layer with LSTM units and dropout regularization with 20% probability

\(144 \times 14 = 2016\)

Dense layer with 8 units

\((14+1) \times 8 = 120\)

Output layer

\((8+1) \times 1 = 9\)

Back to article page