AI RESEARCH
FastOmniTMAE: Parallel Clause Learning for Scalable and Hardware-Efficient Tsetlin Embeddings
arXiv CS.LG
•
ArXi:2605.06982v1 Announce Type: new Embedding models in natural language processing (NLP) increasingly rely on deep architectures such as BERT, while simpler models such as Word2Vec provide efficient representations but limited interpretability. The Tsetlin Machine (TM) offers an alternative logic-based learning paradigm. Omni TM Autoencoder (Omni TM-AE) applies this paradigm to static embedding by exploiting automaton state distributions within a single clause layer, but its