Show Tag: learning-rate

Select Other Tags

Behrens et al. found that humans take into account the volatility of reward probabilities in a reinforcement learning task.

The way they took the volatility into account was qualitatively modelled by a Bayesian learner.

Kleesiek et al. introduce adaptive learning rates to RNNPB which results in faster and more stable training.

RNNPB learns sequences of inputs unsupervised (self-organized).

Learning rate and neighborhood width schedule have to be chosen arbitrarily for (vanilla) SOM training.