A new training-time pruning method for Tsetlin machines removes literals shared by positive and negative clauses, cutting model size by up to 87.54% with at most 3.38% accuracy loss.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ETHEREAL: Energy-efficient and High-throughput Inference using Compressed Tsetlin Machine
A new training-time pruning method for Tsetlin machines removes literals shared by positive and negative clauses, cutting model size by up to 87.54% with at most 3.38% accuracy loss.