Picture for Yoshinari Takeishi

Yoshinari Takeishi

Approximate Spectral Decomposition of Fisher Information Matrix for Simple ReLU Networks

Add code
Nov 30, 2021
Yoshinari Takeishi, Masazumi Iida, Jun'ichi Takeuchi
Figure 1 for Approximate Spectral Decomposition of Fisher Information Matrix for Simple ReLU Networks
Figure 2 for Approximate Spectral Decomposition of Fisher Information Matrix for Simple ReLU Networks
Figure 3 for Approximate Spectral Decomposition of Fisher Information Matrix for Simple ReLU Networks
Figure 4 for Approximate Spectral Decomposition of Fisher Information Matrix for Simple ReLU Networks

We investigate the Fisher information matrix (FIM) of one hidden layer networks with the ReLU activation function and obtain an approximate spectral decomposition of FIM under certain conditions. From this decomposition, we can approximate the main eigenvalues and eigenvectors. We confirmed by numerical simulation that the obtained decomposition is approximately correct when the number of hidden nodes is about 10000.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon