The Sparse Tsetlin Machine: Sparse Representation with Active Literals

arXiv:2405.02375v1 Announce Type: new
Abstract: This paper introduces the Sparse Tsetlin Machine (STM), a novel Tsetlin Machine (TM) that processes sparse data efficiently. Traditionally, the TM does not consider data characteristics such as sparsity, commonly seen in NLP applications and other bag-of-word-based representations. Consequently, a TM must initialize, store, and process a significant number of zero values, resulting in excessive memory usage and computational time. Previous attempts at creating a sparse TM have predominantly been unsuccessful, primarily due to their …

abstract applications arxiv bag cs.ai cs.fl cs.lg data machine nlp novel paper process processes representation sparsity store type word