A novel algorithm learns sparsity thresholds in reservoir computing via gradient descent on neuron-specific thresholds combined with MCMC on a global threshold, inspired by Drosophila neurobiology, and outperforms standard gradient descent on two tasks.
The echo state approach to analysing and training recurrent neural networks- with an erratum note
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning sparsity in reservoir computing through a novel bio-inspired algorithm
A novel algorithm learns sparsity thresholds in reservoir computing via gradient descent on neuron-specific thresholds combined with MCMC on a global threshold, inspired by Drosophila neurobiology, and outperforms standard gradient descent on two tasks.