Learning automata based energy-efficient AI hardware design for IoT applications

A Wheeldon, R Shafik, T Rahman… - … transactions of the …, 2020 - royalsocietypublishing.org
Energy efficiency continues to be the core design challenge for artificial intelligence (AI)
hardware designers. In this paper, we propose a new AI hardware architecture targeting …

The regression Tsetlin machine: a novel approach to interpretable nonlinear regression

K Darshana Abeyrathna… - … of the Royal …, 2020 - royalsocietypublishing.org
Relying simply on bitwise operators, the recently introduced Tsetlin machine (TM) has
provided competitive pattern classification accuracy in several benchmarks, including text …

Word-level human interpretable scoring mechanism for novel text detection using Tsetlin machines

B Bhattarai, OC Granmo, L Jiao - Applied Intelligence, 2022 - Springer
Recent research in novelty detection focuses mainly on document-level classification,
employing deep neural networks (DNN). However, the black-box nature of DNNs makes it …

[PDF][PDF] The weighted Tsetlin machine: Compressed representations with clause weighting

A Phoulady, OC Granmo, SR Gorji… - arxiv preprint arxiv …, 2019 - researchgate.net
Abstract The Tsetlin Machine (TM) is an interpretable mechanism for pattern recognition that
constructs conjunctive clauses from data. The clauses capture frequent patterns with high …

Intrusion detection with interpretable rules generated using the tsetlin machine

KD Abeyrathna, HSG Pussewalage… - 2020 IEEE …, 2020 - ieeexplore.ieee.org
The rapid deployment in information and communication technologies and internet-based
services have made anomaly based network intrusion detection ever so important for …

Convolutional regression tsetlin machine: An interpretable approach to convolutional regression

D Abeyrathna, OC Granmo, M Goodwin - Proceedings of the 2021 6th …, 2021 - dl.acm.org
The Convolutional Tsetlin Machine (CTM), a variant of Tsetlin Machine (TM), represents
patterns as straightforward AND-rules, to address the high computational complexity and the …

A regression Tsetlin machine with integer weighted clauses for compact pattern representation

KD Abeyrathna, OC Granmo, M Goodwin - arxiv preprint arxiv …, 2020 - arxiv.org
The Regression Tsetlin Machine (RTM) addresses the lack of interpretability impeding state-
of-the-art nonlinear regression models. It does this by using conjunctive clauses in …

The weighted tsetlin machine: compressed representations with weighted clauses

A Phoulady, OC Granmo, SR Gorji… - arxiv preprint arxiv …, 2019 - arxiv.org
The Tsetlin Machine (TM) is an interpretable mechanism for pattern recognition that
constructs conjunctive clauses from data. The clauses capture frequent patterns with high …

On obtaining classification confidence, ranked predictions and auc with tsetlin machines

KD Abeyrathna, OC Granmo… - 2020 IEEE Symposium …, 2020 - ieeexplore.ieee.org
Tsetlin machines (TMs) are a promising approach to machine learning that uses Tsetlin
Automata to produce patterns in propositional logic, leading to binary (hard) classifications …

Explainable reinforcement learning with the tsetlin machine

S Rahimi Gorji, OC Granmo, M Wiering - International Conference on …, 2021 - Springer
Abstract The Tsetlin Machine is a recent supervised machine learning algorithm that has
obtained competitive results in several benchmarks, both in terms of accuracy and resource …