RCRC uses untrained random CNNs and reservoir computing plus evolution strategies to reach claimed state-of-the-art scores in reinforcement learning tasks while avoiding data storage and heavy training.
Effect of shapes of activation functions on predictability in the echo state network
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We investigate prediction accuracy for time series of Echo state networks with respect to several kinds of activation functions. As a result, we found that some kinds of activation functions with an appropriate nonlinearity show high performance compared to the conventional sigmoid function.
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Convolutional Reservoir Computing for World Models
RCRC uses untrained random CNNs and reservoir computing plus evolution strategies to reach claimed state-of-the-art scores in reinforcement learning tasks while avoiding data storage and heavy training.