Sciweavers

Share
NIPS
1994

Analysis of Unstandardized Contributions in Cross Connected Networks

8 years 9 months ago
Analysis of Unstandardized Contributions in Cross Connected Networks
Understanding knowledge representations in neural nets has been a difficult problem. Principal components analysis (PCA) of contributions (products of sending activations and connection weights) has yielded valuable insights into knowledge representations, but much of this work has focused on the correlation matrix of contributions. The present work shows that analyzing the variance-covariance matrix of contributions yields more valid insights by taking account of weights.
Thomas R. Shultz, Yuriko Oshima-Takane, Yoshio Tak
Added 02 Nov 2010
Updated 02 Nov 2010
Type Conference
Year 1994
Where NIPS
Authors Thomas R. Shultz, Yuriko Oshima-Takane, Yoshio Takane
Comments (0)
books