biopython v1.71.0 Bio.NeuralNetwork.BackPropagation.Layer.OutputLayer
Initialize the Output Layer.
Arguments:
- num_nodes — The number of nodes in this layer. This corresponds to the number of outputs in the neural network.
- activation — The transformation function used to transform predicted values.
Link to this section Summary
Functions
Calculate the backpropagation error at a given node
Return the error value at a particular node
Update the value of output nodes from the previous layers
Link to this section Functions
Link to this function
__init__()
Link to this function
backpropagate()
Calculate the backpropagation error at a given node.
This calculates the error term using the formula:
p = (z - t) z (1 - z)
where z is the calculated value for the node, and t is the real value.
Arguments:
- outputs - The list of output values we use to calculate the errors in our predictions.
Link to this function
get_error()
Return the error value at a particular node.
Link to this function
update()
Update the value of output nodes from the previous layers.
Arguments:
- previous_layer — The hidden layer preceding this.