A--D. Learned parameter distributions. The initial (yellow) and learned (green) distributions of parameters across neurons in single example networks are shown for the L-MNIST task. Results are shown for both homogeneous initialization (A) and heterogeneous initialization (B). Under both initialization schemes, heterogeneity in neuronal parameters is learned.
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.