predict_gru

Implementation of a Recurrent Neural Network architectures in native R, including Long Short-Term Memory (Hochreiter and Schmidhuber, <doi:10.1162/neco.1997.9.8.1735>), Gated Recurrent Unit (Chung et al., <arXiv:1412.3555>) and vanilla RNN.

Bastiaan Quast

Recurrent Neural Network

predict_gru function

<dl><dt>model</dt>
<dd>output of the trainr function</dd>
<dt>X</dt>
<dd>array of input values, dim 1: samples, dim 2: time, dim 3: variables (could be 1 or more, if a matrix, will be coerce to array)</dd>
<dt>hidden</dt>
<dd>should the function output the hidden units states</dd>
<dt>real_output</dt>
<dd>option used when the function in called inside trainr, do not drop factor for 2 dimension array output</dd>
<dt>...</dt>
<dd>arguments to pass on to sigmoid function</dd></dl>

Arguments

gru prediction function — predict_gru

<dl>

<dt>model</dt>
<dd>output of the trainr function</dd>


<dt>X</dt>
<dd>array of input values, dim 1: samples, dim 2: time, dim 3: variables (could be 1 or more, if a matrix, will be coerce to array)</dd>


<dt>hidden</dt>
<dd>should the function output the hidden units states</dd>


<dt>real_output</dt>
<dd>option used when the function in called inside trainr, do not drop factor for 2 dimension array output</dd>


<dt>...</dt>
<dd>arguments to pass on to sigmoid function</dd>

</dl>

predict_gru: gru prediction function

Description

Usage

Value

Arguments