FEA introduces rational approximations to Shannon entropy and symmetrized KL that are non-singular, require few operations, achieve low error, and yield faster better ML feature selection than LASSO.
Efficient mitchell’s approximate log multipliers for convolutional neural networks.IEEE Transactions on Computers, 68(5):660–675
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fast, close, non-singular and property-preserving approximations of entropic measures
FEA introduces rational approximations to Shannon entropy and symmetrized KL that are non-singular, require few operations, achieve low error, and yield faster better ML feature selection than LASSO.