What is neural network modularity?
If a neural network
Neural network
A simulated network of nodes (‘neurons’) and their connections (weights). Neural networks are the core component of deep learning, the leading AI paradigm.
Making networks more modular is useful to us if the modules represent concepts which we can understand because this helps us understand the whole system better.
Relevant papers about modularity are Neural Networks are Surprisingly Modular, Clusterability in Neural Networks, and Detecting Modularity in Deep Neural Networks.