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

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

Learn Before

Related

Related