Your History

Menu

\( \mathcal{b} \)

Short Description

This symbol represents the bias of a layer in a neural network.

Medium Description

This symbol represents the bias of a layer in a neural network. This constant value is added to the logits before the activation function is used.

Long Description

The symbol \(\mathcal{b}\) represents the bias of a layer in a neural network. This constant value is added to the logits before the activation function is used. The bias helps in shifting the curve of the resulting distribution which aids in modelling non-linear data.

References

  1. Jaeger, H. (n.d.). Neural Networks (AI) (WBAI028-05) Lecture Notes BSc program in Artificial Intelligence. Retrieved April 28, 2024, from https://www.ai.rug.nl/minds/uploads/LN_NN_RUG.pdf