Toggle Main Menu Toggle Search

Open Access padlockePrints

Visualization of Machine Learning Dynamics in Tsetlin Machines

Lookup NU author(s): Dr Ashur Rafiev, Dr Jordan Morris, Dr Fei Xia, Dr Rishad Shafik, Professor Alex Yakovlev


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


The black-box approach towards machine learning models is not helpful for creating fast and efficient implementations. Optimization of these models requires a clear understanding of every aspect of the system, including the architecture, algorithms, and dynamics of the training process. This paper presents a range of visualizations for investigating the dynamics of the Tsetlin Machine, which is a new machine learning algorithm with logic underpinning. These include static visualizations such as architecture and algorithm diagrams and dynamic visualizations such as plotting the evolution of the internal state of the machine. The workflow that supports the visualizations is generalized into an extendable open-source development kit that can be used with future generations of Tsetlin Machines. The example visualization diagrams from the MNIST dataset are discussed from the viewpoint of parallel implementation, hardware acceleration, and opportunities for architectural optimization.

Publication metadata

Author(s): Rafiev A, Morris J, Xia F, Shafik R, Yakovlev A, Granmo O-C, Brown AD

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: First International Symposium on the Tsetlin Machine (ISTM)

Year of Conference: 2022

Online publication date: 21/06/2022

Acceptance date: 22/04/2022

Date deposited: 13/06/2022

Publisher: IEEE