Bilinear

neuralpy.layers.linear.Bilinear(n_nodes, n1_features=None, n2_features=None, bias=True, name=None)

info

Bilinear Layer is mostly stable and can be used for any project. In the future, any chance of breaking changes is very low.

Bilinear layer performs a bilinear transformation of the input.

To learn more about Bilinear layers, please check pytorch documentation for it.

Supported Arguments

• n_nodes: (Integer) Size of the output sample
• n1_features=None: (Integer) Size of the input sample 1, no need for this argument layers except the initial layer
• n2_features=None: (Integer) Size of the input sample 2, no need for this argument layers except the initial layer
• bias=True: (Boolean) If true then uses the bias
• name=None: (String) Name of the layer, if not provided then automatically calculates a unique name for the layer

Example Code

from neuralpy.models import Sequential

from neuralpy.layers.linear import Bilinear

# Making the model

model = Sequential()

model.add(Bilinear(n_nodes=256, n1_features=30, n2_features=40, bias=True, name="Input Layer"))