Effective dimensionality and participation ratio

OG Olivia Gozel
WG Wulfram Gerstner
request Request a Protocol
ask Ask a question
Favorite

The effective dimensionality of the input is measured as the participation ratio (PR) defined as PR=(Tr(C))2/Tr(C2), where C is the covariance matrix of the input patterns, and Tr(C) denotes the trace of matrix C (Mazzucato et al., 2016; Litwin-Kumar et al., 2017).

Do you have any questions about this protocol?

Post your question to gather feedback from the community. We will also invite the authors of this article to respond.

post Post a Question
0 Q&A