A greedy algorithm that adds neurons one at a time, each chosen to maximize joint mutual information, improves spike-encoding classification accuracy in two neuromorphic tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Maximizing Information in Neuron Populations for Neuromorphic Spike Encoding
A greedy algorithm that adds neurons one at a time, each chosen to maximize joint mutual information, improves spike-encoding classification accuracy in two neuromorphic tasks.