A masking regularizer (coordinated dropout) and a sample-based validation metric make sequential autoencoders for spiking data tunable with small datasets.
Gaussian process based nonlinear latent structure discovery in multivariate spike train data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enabling hyperparameter optimization in sequential autoencoders for spiking neural data
A masking regularizer (coordinated dropout) and a sample-based validation metric make sequential autoencoders for spiking data tunable with small datasets.