Learning automata based energy-efficient AI hardware design for IoT applications
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 …
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 …
provided competitive pattern classification accuracy in several benchmarks, including text …
Word-level human interpretable scoring mechanism for novel text detection using Tsetlin machines
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 …
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
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 …
constructs conjunctive clauses from data. The clauses capture frequent patterns with high …
Intrusion detection with interpretable rules generated using the tsetlin machine
The rapid deployment in information and communication technologies and internet-based
services have made anomaly based network intrusion detection ever so important for …
services have made anomaly based network intrusion detection ever so important for …
Convolutional regression tsetlin machine: An interpretable approach to convolutional regression
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 …
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
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 …
of-the-art nonlinear regression models. It does this by using conjunctive clauses in …
The weighted tsetlin machine: compressed representations with weighted clauses
The Tsetlin Machine (TM) is an interpretable mechanism for pattern recognition that
constructs conjunctive clauses from data. The clauses capture frequent patterns with high …
constructs conjunctive clauses from data. The clauses capture frequent patterns with high …
On obtaining classification confidence, ranked predictions and auc with tsetlin machines
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 …
Automata to produce patterns in propositional logic, leading to binary (hard) classifications …
Explainable reinforcement learning with the tsetlin machine
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 …
obtained competitive results in several benchmarks, both in terms of accuracy and resource …