Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

FastOmniTMAE: Parallel Clause Learning for Scalable and Hardware-Efficient Tsetlin Embeddings

About

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 training process remains slow. In this work, we propose FastOmniTMAE, a reformulation of Omni TM-AE that replaces sequential training dependencies with a two-stage parallel process: evaluation and update. Using a Single-Run Multi-Environment Benchmark covering classification, similarity, and clustering, FastOmniTMAE achieves up to 5$\times$ faster training in classification while maintaining comparable embedding quality under both Spearman and Kendall similarity measures. To address the limited efficiency of TM training on conventional GPUs, we further implement FastOmniTMAE as a reusable accelerator on SoC-FPGA platforms. The Multi-Hardware Benchmark shows that FastOmniTMAE achieves similarity scores of 0.669 on a resource-constrained FPGA and 0.696 on an UltraScale+ SoC, demonstrating efficient logic-based embedding training with a small hardware footprint.

Ahmed K. Kadhim, Lei Jiao, Rishad Shafik, Ole-Christoffer Granmo, Mayur Kishor Shende• 2026

Related benchmarks

TaskDatasetResultRank
Word SimilarityMEN
Spearman Rho0.586
74
Word SimilarityMechanical Turk-771
Spearman ρ0.477
14
Word SimilarityMTurk-287
Spearman Correlation0.498
12
Word SimilarityWS-353 SIM
Spearman Correlation0.47
12
Word SimilarityWord-similarity Suite Avg.
Spearman Correlation (ρ)0.537
6
Showing 5 of 5 rows

Other info

Follow for update