Massively parallel and asynchronous tsetlin machine architecture supporting almost constant-time scaling
KD Abeyrathna, B Bhattarai… - International …, 2021 - proceedings.mlr.press
Using logical clauses to represent patterns, Tsetlin Machine (TM) have recently obtained
competitive performance in terms of accuracy, memory footprint, energy, and learning speed …
competitive performance in terms of accuracy, memory footprint, energy, and learning speed …
Explainable tsetlin machine framework for fake news detection with credibility score assessment
The proliferation of fake news, ie, news intentionally spread for misinformation, poses a
threat to individuals and society. Despite various fact-checking websites such as PolitiFact …
threat to individuals and society. Despite various fact-checking websites such as PolitiFact …
On the Convergence of Tsetlin Machines for the IDENTITY-and NOT Operators
The Tsetlin Machine (TM) is a recent machine learning algorithm with several distinct
properties, such as interpretability, simplicity, and hardware-friendliness. Although …
properties, such as interpretability, simplicity, and hardware-friendliness. Although …
Low-power audio keyword spotting using tsetlin machines
The emergence of artificial intelligence (AI) driven keyword spotting (KWS) technologies has
revolutionized human to machine interaction. Yet, the challenge of end-to-end energy …
revolutionized human to machine interaction. Yet, the challenge of end-to-end energy …
On the convergence of tsetlin machines for the xor operator
The Tsetlin Machine (TM) is a novel machine learning algorithm with several distinct
properties, including transparent inference and learning using hardware-near building …
properties, including transparent inference and learning using hardware-near building …
Using tsetlin machine to discover interpretable rules in natural language processing applications
Tsetlin Machines (TM) use finite state machines for learning and propositional logic to
represent patterns. The resulting pattern recognition approach captures information in the …
represent patterns. The resulting pattern recognition approach captures information in the …
Building concise logical patterns by constraining Tsetlin Machine clause size
Tsetlin machine (TM) is a logic-based machine learning approach with the crucial
advantages of being transparent and hardware-friendly. While TMs match or surpass deep …
advantages of being transparent and hardware-friendly. While TMs match or surpass deep …
An interpretable knowledge representation framework for natural language processing with cross-domain application
Data representation plays a crucial role in natural language processing (NLP), forming the
foundation for most NLP tasks. Indeed, NLP performance highly depends upon the …
foundation for most NLP tasks. Indeed, NLP performance highly depends upon the …
[PDF][PDF] Interpretability in Word Sense Disambiguation using Tsetlin Machine.
Word Sense Disambiguation (WSD) is a longstanding unresolved task in Natural Language
Processing. The challenge lies in the fact that words with the same spelling can have …
Processing. The challenge lies in the fact that words with the same spelling can have …
ConvTextTM: An explainable convolutional Tsetlin machine framework for text classification
Recent advancements in natural language processing (NLP) have reshaped the industry,
with powerful language models such as GPT-3 achieving superhuman performance on …
with powerful language models such as GPT-3 achieving superhuman performance on …