https://towardsdatascience.com/neural-network-architectures-156e5bad51ba

University of Michigan - Ann Arbor

The bottleneck layer reduces the training time by diminishing the number of features and operations. By reducing the number of nodes of a newer layer in comparison to previous layers, you can reduce dimensionality.

As shown in the figure, the bottom architecture requires 120 M computations, but by adding the bottleneck layer in the middle, in the architecture shown on top, the number of computations is reduced to 12.4 M.

Bottleneck Layer in Inception Network

Bottleneck layer

http://datahacker.rs/deep-learning-inception-network/

Learn Before

Related