People who code: we want your input. Take the Survey

For questions about "bottlenecks" in dimensional reduction, typically in reference to Artificial Neural Networks and Autoencoders.

The bottleneck in a neural network is just a layer with less neurons then the layer below or above it. Having such a layer encourages the network to compress feature representations to best fit in the available space, in order to get the best loss during training.

Source: What is the concept of Tensorflow Bottlenecks? (SE:AI)