Part of Advances in Neural Information Processing Systems 7 (NIPS 1994)
Thomas Shultz, Yuriko Oshima-Takane, Yoshio Takane
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.