Gpt (generative pre-trained transformer)–a comprehensive review on enabling technologies, potential applications, emerging challenges, and future directions

G Yenduri, M Ramalingam, GC Selvi, Y Supriya… - IEEE …, 2024 - ieeexplore.ieee.org
The Generative Pre-trained Transformer (GPT) represents a notable breakthrough in the
domain of natural language processing, which is propelling us toward the development of …

On the convergence of tsetlin machines for the xor operator

L Jiao, X Zhang, OC Granmo… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The Tsetlin Machine (TM) is a novel machine learning algorithm with several distinct
properties, including transparent inference and learning using hardware-near building …

An interpretable knowledge representation framework for natural language processing with cross-domain application

B Bhattarai, OC Granmo, L Jiao - European Conference on Information …, 2023 - Springer
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 …

Vdhla: Variable depth hybrid learning automaton and its application to defense against the selfish mining attack in bitcoin

A Nikhalat-Jahromi, AM Saghiri… - arXiv preprint arXiv …, 2023 - arxiv.org
Learning Automaton (LA) is an adaptive self-organized model that improves its action-
selection through interaction with an unknown environment. LA with finite action set can be …

BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions

A Bohra, G Verkes, A Harutyunyan… - arXiv preprint arXiv …, 2023 - arxiv.org
Text classification is a well-studied and versatile building block for many NLP applications.
Yet, existing approaches require either large annotated corpora to train a model with or …

Asymmetric variable depth learning automaton and its application in defending against selfish mining attacks on bitcoin

A Nikhalat-Jahromi, AM Saghiri, MR Meybodi - Applied Soft Computing, 2025 - Elsevier
Learning Automaton (LA), a branch of reinforcement learning, initially began with the Fixed
Structure Learning Automaton (FSLA) family and was later expanded to include the Variable …

Weakly Supervised Veracity Classification with LLM-Predicted Credibility Signals

JA Leite, O Razuvayevskaya, K Bontcheva, C Scarton - 2024 - researchsquare.com
Credibility signals represent a wide range of heuristics typically used by journalists and fact-
checkers to assess the veracity of online content. Automating the extraction of credibility …

Hmltnet: multi-modal fake news detection via hierarchical multi-grained features fused with global latent topic

S Cui, L Gong, T Li - Neural Computing and Applications, 2025 - Springer
Since the adverse impact of fake news, especially multi-modal fake news, on public decision-
making and social governance, multi-modal fake news detection has lately attracted …

[HTML][HTML] Hawk: an industrial-strength multi-label document classifier

A Javeed - Natural Language Processing Journal, 2024 - Elsevier
There are a plethora of methods for solving the classical multi-label document classification
problem. However, when it comes to deployment and usage in an industry setting, most if …

Modeling prediction uncertainty in regression using the regression tsetlin machine

KD Abeyrathna, A Hafver… - … Symposium on the Tsetlin …, 2023 - ieeexplore.ieee.org
Machine learning is being widely used in various industries, and its impact varies based on
the application. However, high-risk domains like autonomous vehicles and medical imaging …