Larger values of the meta-prior translate into better reconstruction of the training patterns. The four graphs show a training pattern (in orange) and its reconstruction by PV-RNN (in blue) for different values of . Overlapping sections are in dark gray. For , the target sequence is completely regenerated. When is equal to 0.025 and 0.01, all deterministic steps are correctly reproduced, but regenerated patterns begin to diverge at the 11th and 8th step, respectively. When is set to 0.0001, even the deterministic transition rules fail to be reproduced, and the signals diverge at the 6th time step.
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.