Quantifying Local Specialization in Deep Neural Networks

Understand

A neural network is locally specialized to the extent that parts of its computational graph (i.e.

• structure) can be abstractly represented as performing some comprehensible sub-task relevant to the overall task (i.e.
• functionality).
• Are modern deep neural networks locally specialized? How can this be quantified? In this paper, we consider the problem of taking a neural network whose neurons are partitioned into clusters, and quantifying how functionally specialized the clusters are.